CINXE.COM

<!DOCTYPE html> <html lang="en"> <head> <title>Graphics </title> <meta name="viewport" content="width=device-width, initial-scale=1"> <link rel="apple-touch-icon" sizes="180x180" href="/static/browse/0.3.4/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="/static/browse/0.3.4/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="/static/browse/0.3.4/images/icons/favicon-16x16.png"> <link rel="manifest" href="/static/browse/0.3.4/images/icons/site.webmanifest"> <link rel="mask-icon" href="/static/browse/0.3.4/images/icons/safari-pinned-tab.svg" color="#5bbad5"> <meta name="msapplication-TileColor" content="#da532c"> <meta name="theme-color" content="#ffffff"> <link rel="stylesheet" type="text/css" media="screen" href="/static/browse/0.3.4/css/arXiv.css?v=20241206" /> <link rel="stylesheet" type="text/css" media="print" href="/static/browse/0.3.4/css/arXiv-print.css?v=20200611" /> <link rel="stylesheet" type="text/css" media="screen" href="/static/browse/0.3.4/css/browse_search.css" /> <script language="javascript" src="/static/browse/0.3.4/js/accordion.js" /></script> <script src="/static/browse/0.3.4/js/mathjaxToggle.min.js" type="text/javascript"></script> <script type="text/javascript" language="javascript">mathjaxToggle();</script> </head> <body class="with-cu-identity"> <div class="flex-wrap-footer"> <header> <a href="#content" class="is-sr-only">Skip to main content</a>  <div class="columns is-vcentered is-hidden-mobile" id="cu-identity"> <div class="column" id="cu-logo"> <a href="https://www.cornell.edu/"><img src="/static/browse/0.3.4/images/icons/cu/cornell-reduced-white-SMALL.svg" alt="Cornell University" /></a> </div><div class="column" id="support-ack"> <span id="support-ack-url">We gratefully acknowledge support from the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors.</span> <a href="https://info.arxiv.org/about/donate.html" class="btn-header-donate">Donate</a> </div> </div> <div id="header" class="is-hidden-mobile"> <a aria-hidden="true" tabindex="-1" href="/IgnoreMe"></a> <div class="header-breadcrumbs"> <a href="/"><img src="/static/browse/0.3.4/images/arxiv-logo-one-color-white.svg" alt="arxiv logo" style="height:40px;"/></a> <span>></span> <a href="/list/cs.GR/recent">cs.GR</a> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div> <div class="mobile-header"> <div class="columns is-mobile"> <div class="column logo-arxiv"><a href="https://arxiv.org/"><img src="/static/browse/0.3.4/images/arxiv-logomark-small-white.svg" alt="arXiv logo" style="height:60px;" /></a></div> <div class="column logo-cornell"><a href="https://www.cornell.edu/"> <picture> <source media="(min-width: 501px)" srcset="/static/browse/0.3.4/images/icons/cu/cornell-reduced-white-SMALL.svg 400w" sizes="400w" /> <source srcset="/static/browse/0.3.4/images/icons/cu/cornell_seal_simple_black.svg 2x" /> <img src="/static/browse/0.3.4/images/icons/cu/cornell-reduced-white-SMALL.svg" alt="Cornell University Logo" /> </picture> </a></div> <div class="column nav" id="toggle-container" role="menubar"> <button class="toggle-control"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-white"><title>open search</title><path d="M505 442.7L405.3 343c-4.5-4.5-10.6-7-17-7H372c27.6-35.3 44-79.7 44-128C416 93.1 322.9 0 208 0S0 93.1 0 208s93.1 208 208 208c48.3 0 92.7-16.4 128-44v16.3c0 6.4 2.5 12.5 7 17l99.7 99.7c9.4 9.4 24.6 9.4 33.9 0l28.3-28.3c9.4-9.4 9.4-24.6.1-34zM208 336c-70.7 0-128-57.2-128-128 0-70.7 57.2-128 128-128 70.7 0 128 57.2 128 128 0 70.7-57.2 128-128 128z"/></svg></button> <div class="mobile-toggle-block toggle-target"> <form class="mobile-search-form" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <input class="input" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <input type="hidden" name="source" value="header"> <input type="hidden" name="searchtype" value="all"> <button class="button">GO</button> </div> </form> </div> <button class="toggle-control"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-white" role="menu"><title>open navigation menu</title><path d="M16 132h416c8.837 0 16-7.163 16-16V76c0-8.837-7.163-16-16-16H16C7.163 60 0 67.163 0 76v40c0 8.837 7.163 16 16 16zm0 160h416c8.837 0 16-7.163 16-16v-40c0-8.837-7.163-16-16-16H16c-8.837 0-16 7.163-16 16v40c0 8.837 7.163 16 16 16zm0 160h416c8.837 0 16-7.163 16-16v-40c0-8.837-7.163-16-16-16H16c-8.837 0-16 7.163-16 16v40c0 8.837 7.163 16 16 16z"/ ></svg></button> <div class="mobile-toggle-block toggle-target"> <nav class="mobile-menu" aria-labelledby="mobilemenulabel"> <h2 id="mobilemenulabel">quick links</h2> <ul> <li><a href="https://arxiv.org/login">Login</a></li> <li><a href="https://info.arxiv.org/help">Help Pages</a></li> <li><a href="https://info.arxiv.org/about">About</a></li> </ul> </nav> </div> </div> </div> </div> </header> <main> <div id="content"> <div id='content-inner'> <div id='dlpage'> <h1>Graphics</h1> <ul> <li><a href="#item0">New submissions</a></li> <li><a href="#item8">Cross-lists</a></li> <li><a href="#item11">Replacements</a></li> </ul> <p>See <a id="recent-cs.GR" aria-labelledby="recent-cs.GR" href="/list/cs.GR/recent">recent</a> articles</p> <h3>Showing new listings for Tuesday, 18 March 2025</h3> <div class='paging'>Total of 24 entries </div> <div class='morefewer'>Showing up to 2000 entries per page: <a href=/list/cs.GR/new?skip=0&show=1000 rel="nofollow"> fewer</a> | <span style="color: #454545">more</span> | <span style="color: #454545">all</span> </div> <dl id='articles'> <h3>New submissions (showing 7 of 7 entries)</h3> <dt> <a name='item1'>[1]</a> <a href ="/abs/2503.11801" title="Abstract" id="2503.11801"> arXiv:2503.11801 </a> [<a href="/pdf/2503.11801" title="Download PDF" id="pdf-2503.11801" aria-labelledby="pdf-2503.11801">pdf</a>, <a href="https://arxiv.org/html/2503.11801v1" title="View HTML" id="html-2503.11801" aria-labelledby="html-2503.11801" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.11801" title="Other formats" id="oth-2503.11801" aria-labelledby="oth-2503.11801">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Huang,+X">Xiaoyu Huang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Truong,+T">Takara Truong</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Zhang,+Y">Yunbo Zhang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Yu,+F">Fangzhou Yu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Sleiman,+J+P">Jean Pierre Sleiman</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Hodgins,+J">Jessica Hodgins</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Koushil">Koushil Sreenath</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Farshidian,+F">Farbod Farshidian</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Machine Learning (cs.LG); Robotics (cs.RO) </div> <p class='mathjax'> We present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation. While existing kinematics motion generation with diffusion models offer intuitive steering capabilities with inference-time conditioning, they often fail to produce physically viable motions. In contrast, recent diffusion-based control policies have shown promise in generating physically realizable motion sequences, but the lack of kinematics prediction limits their steerability. Diffuse-CLoC addresses these challenges through a key insight: modeling the joint distribution of states and actions within a single diffusion model makes action generation steerable by conditioning it on the predicted states. This approach allows us to leverage established conditioning techniques from kinematic motion generation while producing physically realistic motions. As a result, we achieve planning capabilities without the need for a high-level planner. Our method handles a diverse set of unseen long-horizon downstream tasks through a single pre-trained model, including static and dynamic obstacle avoidance, motion in-betweening, and task-space control. Experimental results show that our method significantly outperforms the traditional hierarchical framework of high-level motion diffusion and low-level tracking. </p> </div> </dd> <dt> <a name='item2'>[2]</a> <a href ="/abs/2503.11978" title="Abstract" id="2503.11978"> arXiv:2503.11978 </a> [<a href="/pdf/2503.11978" title="Download PDF" id="pdf-2503.11978" aria-labelledby="pdf-2503.11978">pdf</a>, <a href="https://arxiv.org/html/2503.11978v1" title="View HTML" id="html-2503.11978" aria-labelledby="html-2503.11978" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.11978" title="Other formats" id="oth-2503.11978" aria-labelledby="oth-2503.11978">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Chen,+E+M">Eric M. Chen</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Liu,+D">Di Liu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Ma,+S">Sizhuo Ma</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Vasilkovsky,+M">Michael Vasilkovsky</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Zhou,+B">Bing Zhou</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Gao,+Q">Qiang Gao</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+W">Wenzhou Wang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Luo,+J">Jiahao Luo</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Metaxas,+D+N">Dimitris N. Metaxas</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Sitzmann,+V">Vincent Sitzmann</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+J">Jian Wang</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> N/A </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> The increasing popularity of personalized avatar systems, such as Snapchat Bitmojis and Apple Memojis, highlights the growing demand for digital self-representation. Despite their widespread use, existing avatar platforms face significant limitations, including restricted expressivity due to predefined assets, tedious customization processes, or inefficient rendering requirements. Addressing these shortcomings, we introduce Snapmoji, an avatar generation system that instantly creates animatable, dual-stylized avatars from a selfie. We propose Gaussian Domain Adaptation (GDA), which is pre-trained on large-scale Gaussian models using 3D data from sources such as Objaverse and fine-tuned with 2D style transfer tasks, endowing it with a rich 3D prior. This enables Snapmoji to transform a selfie into a primary stylized avatar, like the Bitmoji style, and apply a secondary style, such as Plastic Toy or Alien, all while preserving the user's identity and the primary style's integrity. Our system is capable of producing 3D Gaussian avatars that support dynamic animation, including accurate facial expression transfer. Designed for efficiency, Snapmoji achieves selfie-to-avatar conversion in just 0.9 seconds and supports real-time interactions on mobile devices at 30 to 40 frames per second. Extensive testing confirms that Snapmoji outperforms existing methods in versatility and speed, making it a convenient tool for automatic avatar creation in various styles. </p> </div> </dd> <dt> <a name='item3'>[3]</a> <a href ="/abs/2503.12174" title="Abstract" id="2503.12174"> arXiv:2503.12174 </a> [<a href="/pdf/2503.12174" title="Download PDF" id="pdf-2503.12174" aria-labelledby="pdf-2503.12174">pdf</a>, <a href="https://arxiv.org/html/2503.12174v1" title="View HTML" id="html-2503.12174" aria-labelledby="html-2503.12174" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.12174" title="Other formats" id="oth-2503.12174" aria-labelledby="oth-2503.12174">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> DPCS: Path Tracing-Based Differentiable Projector-Camera Systems </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+J">Jijiang Li</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Deng,+Q">Qingyue Deng</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Ling,+H">Haibin Ling</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Huang,+B">Bingyao Huang</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> 16 pages,16 figures </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> Projector-camera systems (ProCams) simulation aims to model the physical project-and-capture process and associated scene parameters of a ProCams, and is crucial for spatial augmented reality (SAR) applications such as ProCams relighting and projector compensation. Recent advances use an end-to-end neural network to learn the project-and-capture process. However, these neural network-based methods often implicitly encapsulate scene parameters, such as surface material, gamma, and white balance in the network parameters, and are less interpretable and hard for novel scene simulation. Moreover, neural networks usually learn the indirect illumination implicitly in an image-to-image translation way which leads to poor performance in simulating complex projection effects such as soft-shadow and interreflection. In this paper, we introduce a novel path tracing-based differentiable projector-camera systems (DPCS), offering a differentiable ProCams simulation method that explicitly integrates multi-bounce path tracing. Our DPCS models the physical project-and-capture process using differentiable physically-based rendering (PBR), enabling the scene parameters to be explicitly decoupled and learned using much fewer samples. Moreover, our physically-based method not only enables high-quality downstream ProCams tasks, such as ProCams relighting and projector compensation, but also allows novel scene simulation using the learned scene parameters. In experiments, DPCS demonstrates clear advantages over previous approaches in ProCams simulation, offering better interpretability, more efficient handling of complex interreflection and shadow, and requiring fewer training samples. </p> </div> </dd> <dt> <a name='item4'>[4]</a> <a href ="/abs/2503.12229" title="Abstract" id="2503.12229"> arXiv:2503.12229 </a> [<a href="/pdf/2503.12229" title="Download PDF" id="pdf-2503.12229" aria-labelledby="pdf-2503.12229">pdf</a>, <a href="https://arxiv.org/html/2503.12229v1" title="View HTML" id="html-2503.12229" aria-labelledby="html-2503.12229" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.12229" title="Other formats" id="oth-2503.12229" aria-labelledby="oth-2503.12229">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Shadow Art Kanji: Inverse Rendering Application </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Rothman,+W+L">William Louis Rothman</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Matsushita,+Y">Yasuyuki Matsushita</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> 7 pages, 10 figures, 8 references </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> Finding a balance between artistic beauty and machine-generated imagery is always a difficult task. This project seeks to create 3D models that, when illuminated, cast shadows resembling Kanji characters. It aims to combine artistic expression with computational techniques, providing an accurate and efficient approach to visualizing these Japanese characters through shadows. </p> </div> </dd> <dt> <a name='item5'>[5]</a> <a href ="/abs/2503.12291" title="Abstract" id="2503.12291"> arXiv:2503.12291 </a> [<a href="/pdf/2503.12291" title="Download PDF" id="pdf-2503.12291" aria-labelledby="pdf-2503.12291">pdf</a>, <a href="https://arxiv.org/html/2503.12291v1" title="View HTML" id="html-2503.12291" aria-labelledby="html-2503.12291" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.12291" title="Other formats" id="oth-2503.12291" aria-labelledby="oth-2503.12291">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Text-Driven Video Style Transfer with State-Space Models: Extending StyleMamba for Temporal Coherence </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+C">Chao Li</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Park,+M">Minsu Park</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Rossi,+C">Cristina Rossi</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+Z">Zhuang Li</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span> </div> <p class='mathjax'> StyleMamba has recently demonstrated efficient text-driven image style transfer by leveraging state-space models (SSMs) and masked directional losses. In this paper, we extend the StyleMamba framework to handle video sequences. We propose new temporal modules, including a \emph{Video State-Space Fusion Module} to model inter-frame dependencies and a novel \emph{Temporal Masked Directional Loss} that ensures style consistency while addressing scene changes and partial occlusions. Additionally, we introduce a \emph{Temporal Second-Order Loss} to suppress abrupt style variations across consecutive frames. Our experiments on DAVIS and UCF101 show that the proposed approach outperforms competing methods in terms of style consistency, smoothness, and computational efficiency. We believe our new framework paves the way for real-time text-driven video stylization with state-of-the-art perceptual results. </p> </div> </dd> <dt> <a name='item6'>[6]</a> <a href ="/abs/2503.12553" title="Abstract" id="2503.12553"> arXiv:2503.12553 </a> [<a href="/pdf/2503.12553" title="Download PDF" id="pdf-2503.12553" aria-labelledby="pdf-2503.12553">pdf</a>, <a href="https://arxiv.org/html/2503.12553v1" title="View HTML" id="html-2503.12553" aria-labelledby="html-2503.12553" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.12553" title="Other formats" id="oth-2503.12553" aria-labelledby="oth-2503.12553">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Wu,+X">Xianzu Wu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Ai,+Z">Zhenxin Ai</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Yang,+H">Harry Yang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lim,+S">Ser-Nam Lim</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Liu,+J">Jun Liu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+H">Huan Wang</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> Recent advances in single-view 3D scene reconstruction have highlighted the challenges in capturing fine geometric details and ensuring structural consistency, particularly in high-fidelity outdoor scene modeling. This paper presents Niagara, a new single-view 3D scene reconstruction framework that can faithfully reconstruct challenging outdoor scenes from a single input image for the first time. <br>Our approach integrates monocular depth and normal estimation as input, which substantially improves its ability to capture fine details, mitigating common issues like geometric detail loss and deformation. <br>Additionally, we introduce a geometric affine field (GAF) and 3D self-attention as geometry-constraint, which combines the structural properties of explicit geometry with the adaptability of implicit feature fields, striking a balance between efficient rendering and high-fidelity reconstruction. <br>Our framework finally proposes a specialized encoder-decoder architecture, where a depth-based 3D Gaussian decoder is proposed to predict 3D Gaussian parameters, which can be used for novel view synthesis. Extensive results and analyses suggest that our Niagara surpasses prior SoTA approaches such as Flash3D in both single-view and dual-view settings, significantly enhancing the geometric accuracy and visual fidelity, especially in outdoor scenes. </p> </div> </dd> <dt> <a name='item7'>[7]</a> <a href ="/abs/2503.12814" title="Abstract" id="2503.12814"> arXiv:2503.12814 </a> [<a href="/pdf/2503.12814" title="Download PDF" id="pdf-2503.12814" aria-labelledby="pdf-2503.12814">pdf</a>, <a href="https://arxiv.org/html/2503.12814v1" title="View HTML" id="html-2503.12814" aria-labelledby="html-2503.12814" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.12814" title="Other formats" id="oth-2503.12814" aria-labelledby="oth-2503.12814">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Versatile Physics-based Character Control with Hybrid Latent Representation </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Bae,+J">Jinseok Bae</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Won,+J">Jungdam Won</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lim,+D">Donggeun Lim</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Hwang,+I">Inwoo Hwang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Kim,+Y+M">Young Min Kim</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Artificial Intelligence (cs.AI); Robotics (cs.RO) </div> <p class='mathjax'> We present a versatile latent representation that enables physically simulated character to efficiently utilize motion priors. To build a powerful motion embedding that is shared across multiple tasks, the physics controller should employ rich latent space that is easily explored and capable of generating high-quality motion. We propose integrating continuous and discrete latent representations to build a versatile motion prior that can be adapted to a wide range of challenging control tasks. Specifically, we build a discrete latent model to capture distinctive posterior distribution without collapse, and simultaneously augment the sampled vector with the continuous residuals to generate high-quality, smooth motion without jittering. We further incorporate Residual Vector Quantization, which not only maximizes the capacity of the discrete motion prior, but also efficiently abstracts the action space during the task learning phase. We demonstrate that our agent can produce diverse yet smooth motions simply by traversing the learned motion prior through unconditional motion generation. Furthermore, our model robustly satisfies sparse goal conditions with highly expressive natural motions, including head-mounted device tracking and motion in-betweening at irregular intervals, which could not be achieved with existing latent representations. </p> </div> </dd> </dl> <dl id='articles'> <h3>Cross submissions (showing 3 of 3 entries)</h3> <dt> <a name='item8'>[8]</a> <a href ="/abs/2503.12052" title="Abstract" id="2503.12052"> arXiv:2503.12052 </a> (cross-list from cs.CV) [<a href="/pdf/2503.12052" title="Download PDF" id="pdf-2503.12052" aria-labelledby="pdf-2503.12052">pdf</a>, <a href="https://arxiv.org/html/2503.12052v1" title="View HTML" id="html-2503.12052" aria-labelledby="html-2503.12052" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.12052" title="Other formats" id="oth-2503.12052" aria-labelledby="oth-2503.12052">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Tailor: An Integrated Text-Driven CG-Ready Human and Garment Generation System </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Sun,+Z">Zhiyao Sun</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wen,+Y">Yu-Hui Wen</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lin,+M">Matthieu Lin</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Fang,+H">Ho-Jui Fang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Ye,+S">Sheng Ye</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lv,+T">Tian Lv</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Liu,+Y">Yong-Jin Liu</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> Project page: <a href="https://human-tailor.github.com" rel="external noopener nofollow" class="link-external link-https">this https URL</a> </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Graphics (cs.GR) </div> <p class='mathjax'> Creating detailed 3D human avatars with garments typically requires specialized expertise and labor-intensive processes. Although recent advances in generative AI have enabled text-to-3D human/clothing generation, current methods fall short in offering accessible, integrated pipelines for producing ready-to-use clothed avatars. To solve this, we introduce Tailor, an integrated text-to-avatar system that generates high-fidelity, customizable 3D humans with simulation-ready garments. Our system includes a three-stage pipeline. We first employ a large language model to interpret textual descriptions into parameterized body shapes and semantically matched garment templates. Next, we develop topology-preserving deformation with novel geometric losses to adapt garments precisely to body geometries. Furthermore, an enhanced texture diffusion module with a symmetric local attention mechanism ensures both view consistency and photorealistic details. Quantitative and qualitative evaluations demonstrate that Tailor outperforms existing SoTA methods in terms of fidelity, usability, and diversity. Code will be available for academic use. </p> </div> </dd> <dt> <a name='item9'>[9]</a> <a href ="/abs/2503.12552" title="Abstract" id="2503.12552"> arXiv:2503.12552 </a> (cross-list from cs.CV) [<a href="/pdf/2503.12552" title="Download PDF" id="pdf-2503.12552" aria-labelledby="pdf-2503.12552">pdf</a>, <a href="https://arxiv.org/html/2503.12552v1" title="View HTML" id="html-2503.12552" aria-labelledby="html-2503.12552" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.12552" title="Other formats" id="oth-2503.12552" aria-labelledby="oth-2503.12552">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> MTGS: Multi-Traversal Gaussian Splatting </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+T">Tianyu Li</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Qiu,+Y">Yihang Qiu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wu,+Z">Zhenhua Wu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lindstr%C3%B6m,+C">Carl Lindstr枚m</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Su,+P">Peng Su</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Nie%C3%9Fner,+M">Matthias Nie脽ner</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+H">Hongyang Li</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Graphics (cs.GR) </div> <p class='mathjax'> Multi-traversal data, commonly collected through daily commutes or by self-driving fleets, provides multiple viewpoints for scene reconstruction within a road block. This data offers significant potential for high-quality novel view synthesis, which is crucial for applications such as autonomous vehicle simulators. However, inherent challenges in multi-traversal data often result in suboptimal reconstruction quality, including variations in appearance and the presence of dynamic objects. To address these issues, we propose Multi-Traversal Gaussian Splatting (MTGS), a novel approach that reconstructs high-quality driving scenes from arbitrarily collected multi-traversal data by modeling a shared static geometry while separately handling dynamic elements and appearance variations. Our method employs a multi-traversal dynamic scene graph with a shared static node and traversal-specific dynamic nodes, complemented by color correction nodes with learnable spherical harmonics coefficient residuals. This approach enables high-fidelity novel view synthesis and provides flexibility to navigate any viewpoint. We conduct extensive experiments on a large-scale driving dataset, nuPlan, with multi-traversal data. Our results demonstrate that MTGS improves LPIPS by 23.5% and geometry accuracy by 46.3% compared to single-traversal baselines. The code and data would be available to the public. </p> </div> </dd> <dt> <a name='item10'>[10]</a> <a href ="/abs/2503.12848" title="Abstract" id="2503.12848"> arXiv:2503.12848 </a> (cross-list from physics.optics) [<a href="/pdf/2503.12848" title="Download PDF" id="pdf-2503.12848" aria-labelledby="pdf-2503.12848">pdf</a>, <a href="/format/2503.12848" title="Other formats" id="oth-2503.12848" aria-labelledby="oth-2503.12848">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Introducing GPGPUs to smartphone-based digital holographic microscope for 3D imaging </div> <div class='list-authors'><a href="https://arxiv.org/search/physics?searchtype=author&query=Nagahama,+Y">Yuki Nagahama</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Optics (physics.optics)</span>; Graphics (cs.GR) </div> <p class='mathjax'> Digital holography (DH) enables non-contact, noninvasive 3D imaging of transparent and moving microscopic samples by capturing amplitude and phase information in a single shot. In this work, we present a compact, low-cost, real-time smartphone-based DHM system accelerated by GPUs. The system comprises a 3D-printed optical system using readily available image sensors and lasers, coupled with an Android app for hologram reconstruction, extracting amplitude and phase information. Results show a frame rate improvement of approximately 1.65x compared to a CPU-only system. This inexpensive, compact DHM, combining 3D-printed optics and smartphone-based reconstruction, offers a novel approach compared to existing systems and holds promise for fieldwork and remote diagnostics. </p> </div> </dd> </dl> <dl id='articles'> <h3>Replacement submissions (showing 14 of 14 entries)</h3> <dt> <a name='item11'>[11]</a> <a href ="/abs/2308.13934" title="Abstract" id="2308.13934"> arXiv:2308.13934 </a> (replaced) [<a href="/pdf/2308.13934" title="Download PDF" id="pdf-2308.13934" aria-labelledby="pdf-2308.13934">pdf</a>, <a href="https://arxiv.org/html/2308.13934v2" title="View HTML" id="html-2308.13934" aria-labelledby="html-2308.13934" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2308.13934" title="Other formats" id="oth-2308.13934" aria-labelledby="oth-2308.13934">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Lin,+G">Guying Lin</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Yang,+L">Lei Yang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Zhang,+C">Congyi Zhang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Pan,+H">Hao Pan</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Ping,+Y">Yuhan Ping</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wei,+G">Guodong Wei</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Komura,+T">Taku Komura</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Keyser,+J">John Keyser</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+W">Wenping Wang</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span> </div> <p class='mathjax'> Neural implicit representations are widely used for 3D shape modeling due to their smoothness and compactness, but traditional MLP-based methods struggle with sharp features, such as edges and corners in CAD models, and require long training times. To address these limitations, we propose Patch-Grid, a unified neural implicit representation that efficiently fits complex shapes, preserves sharp features, and handles open boundaries and thin geometric structures. Patch-Grid learns a signed distance field (SDF) for each surface patch using a learnable patch feature volume. To represent sharp edges and corners, it merges the learned SDFs via constructive solid geometry (CSG) operations. A novel merge grid organizes patch feature volumes within a shared octree structure, localizing and simplifying CSG operations. This design ensures robust merging of SDFs and significantly reduces computational complexity, enabling training within seconds while maintaining high fidelity. Experimental results show that Patch-Grid achieves state-of-the-art reconstruction quality for shapes with intricate sharp features, open surfaces, and thin structures, offering superior robustness, efficiency, and accuracy. </p> </div> </dd> <dt> <a name='item12'>[12]</a> <a href ="/abs/2405.12663" title="Abstract" id="2405.12663"> arXiv:2405.12663 </a> (replaced) [<a href="/pdf/2405.12663" title="Download PDF" id="pdf-2405.12663" aria-labelledby="pdf-2405.12663">pdf</a>, <a href="https://arxiv.org/html/2405.12663v2" title="View HTML" id="html-2405.12663" aria-labelledby="html-2405.12663" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2405.12663" title="Other formats" id="oth-2405.12663" aria-labelledby="oth-2405.12663">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> LAGA: Layered 3D Avatar Generation and Customization via Gaussian Splatting </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Gong,+J">Jia Gong</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Ji,+S">Shenyu Ji</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Foo,+L+G">Lin Geng Foo</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Chen,+K">Kang Chen</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Rahmani,+H">Hossein Rahmani</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Liu,+J">Jun Liu</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> Creating and customizing a 3D clothed avatar from textual descriptions is a critical and challenging task. Traditional methods often treat the human body and clothing as inseparable, limiting users' ability to freely mix and match garments. In response to this limitation, we present LAyered Gaussian Avatar (LAGA), a carefully designed framework enabling the creation of high-fidelity decomposable avatars with diverse garments. By decoupling garments from avatar, our framework empowers users to conviniently edit avatars at the garment level. Our approach begins by modeling the avatar using a set of Gaussian points organized in a layered structure, where each layer corresponds to a specific garment or the human body itself. To generate high-quality garments for each layer, we introduce a coarse-to-fine strategy for diverse garment generation and a novel dual-SDS loss function to maintain coherence between the generated garments and avatar components, including the human body and other garments. Moreover, we introduce three regularization losses to guide the movement of Gaussians for garment transfer, allowing garments to be freely transferred to various avatars. Extensive experimentation demonstrates that our approach surpasses existing methods in the generation of 3D clothed humans. </p> </div> </dd> <dt> <a name='item13'>[13]</a> <a href ="/abs/2407.07755" title="Abstract" id="2407.07755"> arXiv:2407.07755 </a> (replaced) [<a href="/pdf/2407.07755" title="Download PDF" id="pdf-2407.07755" aria-labelledby="pdf-2407.07755">pdf</a>, <a href="https://arxiv.org/html/2407.07755v3" title="View HTML" id="html-2407.07755" aria-labelledby="html-2407.07755" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2407.07755" title="Other formats" id="oth-2407.07755" aria-labelledby="oth-2407.07755">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Neural Geometry Processing via Spherical Neural Surfaces </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Williamson,+R">Romy Williamson</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Mitra,+N+J">Niloy J. Mitra</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> 14 pages, 14 figures </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> Neural surfaces (e.g., neural map encoding, deep implicits and neural radiance fields) have recently gained popularity because of their generic structure (e.g., multi-layer perceptron) and easy integration with modern learning-based setups. Traditionally, we have a rich toolbox of geometry processing algorithms designed for polygonal meshes to analyze and operate on surface geometry. In the absence of an analogous toolbox, neural representations are typically discretized and converted into a mesh, before applying any geometry processing algorithm. This is unsatisfactory and, as we demonstrate, unnecessary. In this work, we propose a spherical neural surface representation for genus-0 surfaces and demonstrate how to compute core geometric operators directly on this representation. Namely, we estimate surface normals and first and second fundamental forms of the surface, as well as compute surface gradient, surface divergence and Laplace-Beltrami operator on scalar/vector fields defined on the surface. Our representation is fully seamless, overcoming a key limitation of similar explicit representations such as Neural Surface Maps [Morreale et al. 2021]. These operators, in turn, enable geometry processing directly on the neural representations without any unnecessary meshing. We demonstrate illustrative applications in (neural) spectral analysis, heat flow and mean curvature flow, and evaluate robustness to isometric shape variations. We propose theoretical formulations and validate their numerical estimates, against analytical estimates, mesh-based baselines, and neural alternatives, where available. By systematically linking neural surface representations with classical geometry processing algorithms, we believe that this work can become a key ingredient in enabling neural geometry processing. Code is accessible from the project webpage. </p> </div> </dd> <dt> <a name='item14'>[14]</a> <a href ="/abs/2412.03685" title="Abstract" id="2412.03685"> arXiv:2412.03685 </a> (replaced) [<a href="/pdf/2412.03685" title="Download PDF" id="pdf-2412.03685" aria-labelledby="pdf-2412.03685">pdf</a>, <a href="https://arxiv.org/html/2412.03685v2" title="View HTML" id="html-2412.03685" aria-labelledby="html-2412.03685" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2412.03685" title="Other formats" id="oth-2412.03685" aria-labelledby="oth-2412.03685">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Sprite Sheet Diffusion: Generate Game Character for Animation </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Hsieh,+C">Cheng-An Hsieh</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Zhang,+J">Jing Zhang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Yan,+A">Ava Yan</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> <a href="https://chenganhsieh.github.io/spritesheet-diffusion/" rel="external noopener nofollow" class="link-external link-https">this https URL</a> </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> In the game development process, creating character animations is a vital step that involves several stages. Typically for 2D games, illustrators begin by designing the main character image, which serves as the foundation for all subsequent animations. To create a smooth motion sequence, these subsequent animations involve drawing the character in different poses and actions, such as running, jumping, or attacking. This process requires significant manual effort from illustrators, as they must meticulously ensure consistency in design, proportions, and style across multiple motion frames. Each frame is drawn individually, making this a time-consuming and labor-intensive task. Generative models, such as diffusion models, have the potential to revolutionize this process by automating the creation of sprite sheets. Diffusion models, known for their ability to generate diverse images, can be adapted to create character animations. By leveraging the capabilities of diffusion models, we can significantly reduce the manual workload for illustrators, accelerate the animation creation process, and open up new creative possibilities in game development. </p> </div> </dd> <dt> <a name='item15'>[15]</a> <a href ="/abs/2502.10872" title="Abstract" id="2502.10872"> arXiv:2502.10872 </a> (replaced) [<a href="/pdf/2502.10872" title="Download PDF" id="pdf-2502.10872" aria-labelledby="pdf-2502.10872">pdf</a>, <a href="https://arxiv.org/html/2502.10872v4" title="View HTML" id="html-2502.10872" aria-labelledby="html-2502.10872" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2502.10872" title="Other formats" id="oth-2502.10872" aria-labelledby="oth-2502.10872">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Corotational Hinge-based Thin Plates/Shells </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Liang,+Q">Qixin Liang</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span> </div> <p class='mathjax'> We present six thin plate/shell models, derived from three distinct types of curvature operators formulated within the corotational frame, for simulating both rest-flat and rest-curved triangular meshes. Each curvature operator derives a curvature expression corresponding to both a plate model and a shell model. The corotational edge-based hinge model uses an edge-based stencil to compute directional curvature, while the corotational FVM hinge model utilizes a triangle-centered stencil, applying the finite volume method (FVM) to superposition directional curvatures across edges, yielding a generalized curvature. The corotational smoothed hinge model also employs a triangle-centered stencil but transforms directional curvatures into a generalized curvature based on a quadratic surface fit. All models assume small strain and small curvature, leading to constant bending energy Hessians, which benefit implicit integrators. Through quantitative benchmarks and qualitative elastodynamic simulations with large time steps, we demonstrate the accuracy, efficiency, and stability of these models. Our contributions enhance the thin plate/shell library for use in both computer graphics and engineering applications. </p> </div> </dd> <dt> <a name='item16'>[16]</a> <a href ="/abs/2503.00605" title="Abstract" id="2503.00605"> arXiv:2503.00605 </a> (replaced) [<a href="/pdf/2503.00605" title="Download PDF" id="pdf-2503.00605" aria-labelledby="pdf-2503.00605">pdf</a>, <a href="https://arxiv.org/html/2503.00605v2" title="View HTML" id="html-2503.00605" aria-labelledby="html-2503.00605" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.00605" title="Other formats" id="oth-2503.00605" aria-labelledby="oth-2503.00605">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> GenVDM: Generating Vector Displacement Maps From a Single Image </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Yang,+Y">Yuezhi Yang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Chen,+Q">Qimin Chen</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Kim,+V+G">Vladimir G. Kim</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Chaudhuri,+S">Siddhartha Chaudhuri</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Huang,+Q">Qixing Huang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Chen,+Z">Zhiqin Chen</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> accepted to CVPR2025 </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> We introduce the first method for generating Vector Displacement Maps (VDMs): parameterized, detailed geometric stamps commonly used in 3D modeling. Given a single input image, our method first generates multi-view normal maps and then reconstructs a VDM from the normals via a novel reconstruction pipeline. We also propose an efficient algorithm for extracting VDMs from 3D objects, and present the first academic VDM dataset. Compared to existing 3D generative models focusing on complete shapes, we focus on generating parts that can be seamlessly attached to shape surfaces. The method gives artists rich control over adding geometric details to a 3D shape. Experiments demonstrate that our approach outperforms existing baselines. Generating VDMs offers additional benefits, such as using 2D image editing to customize and refine 3D details. </p> </div> </dd> <dt> <a name='item17'>[17]</a> <a href ="/abs/2503.01425" title="Abstract" id="2503.01425"> arXiv:2503.01425 </a> (replaced) [<a href="/pdf/2503.01425" title="Download PDF" id="pdf-2503.01425" aria-labelledby="pdf-2503.01425">pdf</a>, <a href="https://arxiv.org/html/2503.01425v2" title="View HTML" id="html-2503.01425" aria-labelledby="html-2503.01425" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2503.01425" title="Other formats" id="oth-2503.01425" aria-labelledby="oth-2503.01425">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> MeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+H">Haoxuan Li</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Erkoc,+Z">Ziya Erkoc</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+L">Lei Li</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Sirigatti,+D">Daniele Sirigatti</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Rozov,+V">Vladyslav Rozov</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Dai,+A">Angela Dai</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Nie%C3%9Fner,+M">Matthias Nie脽ner</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> Project page: <a href="https://derkleineli.github.io/meshpad/" rel="external noopener nofollow" class="link-external link-https">this https URL</a> Video: <a href="https://www.youtube.com/watch?v=_T6UTGTMZ1E" rel="external noopener nofollow" class="link-external link-https">this https URL</a> </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Graphics (cs.GR)</span>; Computer Vision and Pattern Recognition (cs.CV) </div> <p class='mathjax'> We introduce MeshPad, a generative approach that creates 3D meshes from sketch inputs. Building on recent advances in artist-designed triangle mesh generation, our approach addresses the need for interactive mesh creation. To this end, we focus on enabling consistent edits by decomposing editing into 'deletion' of regions of a mesh, followed by 'addition' of new mesh geometry. Both operations are invoked by simple user edits of a sketch image, facilitating an iterative content creation process and enabling the construction of complex 3D meshes. Our approach is based on a triangle sequence-based mesh representation, exploiting a large Transformer model for mesh triangle addition and deletion. In order to perform edits interactively, we introduce a vertex-aligned speculative prediction strategy on top of our additive mesh generator. This speculator predicts multiple output tokens corresponding to a vertex, thus significantly reducing the computational cost of inference and accelerating the editing process, making it possible to execute each editing step in only a few seconds. Comprehensive experiments demonstrate that MeshPad outperforms state-of-the-art sketch-conditioned mesh generation methods, achieving more than 22% mesh quality improvement in Chamfer distance, and being preferred by 90% of participants in perceptual evaluations. </p> </div> </dd> <dt> <a name='item18'>[18]</a> <a href ="/abs/2409.12957" title="Abstract" id="2409.12957"> arXiv:2409.12957 </a> (replaced) [<a href="/pdf/2409.12957" title="Download PDF" id="pdf-2409.12957" aria-labelledby="pdf-2409.12957">pdf</a>, <a href="https://arxiv.org/html/2409.12957v2" title="View HTML" id="html-2409.12957" aria-labelledby="html-2409.12957" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2409.12957" title="Other formats" id="oth-2409.12957" aria-labelledby="oth-2409.12957">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Chen,+Z">Zhaoxi Chen</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Tang,+J">Jiaxiang Tang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Dong,+Y">Yuhao Dong</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Cao,+Z">Ziang Cao</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Hong,+F">Fangzhou Hong</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lan,+Y">Yushi Lan</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+T">Tengfei Wang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Xie,+H">Haozhe Xie</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wu,+T">Tong Wu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Saito,+S">Shunsuke Saito</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Pan,+L">Liang Pan</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lin,+D">Dahua Lin</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Liu,+Z">Ziwei Liu</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> CVPR 2025, Code <a href="https://github.com/3DTopia/3DTopia-XL" rel="external noopener nofollow" class="link-external link-https">this https URL</a> Project Page <a href="https://3dtopia.github.io/3DTopia-XL/" rel="external noopener nofollow" class="link-external link-https">this https URL</a> </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Graphics (cs.GR) </div> <p class='mathjax'> The increasing demand for high-quality 3D assets across various industries necessitates efficient and automated 3D content creation. Despite recent advancements in 3D generative models, existing methods still face challenges with optimization speed, geometric fidelity, and the lack of assets for physically based rendering (PBR). In this paper, we introduce 3DTopia-XL, a scalable native 3D generative model designed to overcome these limitations. 3DTopia-XL leverages a novel primitive-based 3D representation, PrimX, which encodes detailed shape, albedo, and material field into a compact tensorial format, facilitating the modeling of high-resolution geometry with PBR assets. On top of the novel representation, we propose a generative framework based on Diffusion Transformer (DiT), which comprises 1) Primitive Patch Compression, 2) and Latent Primitive Diffusion. 3DTopia-XL learns to generate high-quality 3D assets from textual or visual inputs. We conduct extensive qualitative and quantitative experiments to demonstrate that 3DTopia-XL significantly outperforms existing methods in generating high-quality 3D assets with fine-grained textures and materials, efficiently bridging the quality gap between generative models and real-world applications. </p> </div> </dd> <dt> <a name='item19'>[19]</a> <a href ="/abs/2411.14430" title="Abstract" id="2411.14430"> arXiv:2411.14430 </a> (replaced) [<a href="/pdf/2411.14430" title="Download PDF" id="pdf-2411.14430" aria-labelledby="pdf-2411.14430">pdf</a>, <a href="https://arxiv.org/html/2411.14430v2" title="View HTML" id="html-2411.14430" aria-labelledby="html-2411.14430" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2411.14430" title="Other formats" id="oth-2411.14430" aria-labelledby="oth-2411.14430">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Stable Flow: Vital Layers for Training-Free Image Editing </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Avrahami,+O">Omri Avrahami</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Patashnik,+O">Or Patashnik</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Fried,+O">Ohad Fried</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Nemchinov,+E">Egor Nemchinov</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Aberman,+K">Kfir Aberman</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lischinski,+D">Dani Lischinski</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Cohen-Or,+D">Daniel Cohen-Or</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> CVPR 2025. Project page is available at <a href="https://omriavrahami.com/stable-flow" rel="external noopener nofollow" class="link-external link-https">this https URL</a> </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Graphics (cs.GR); Machine Learning (cs.LG) </div> <p class='mathjax'> Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and sampling. However, they exhibit limited generation diversity. In this work, we leverage this limitation to perform consistent image edits via selective injection of attention features. The main challenge is that, unlike the UNet-based models, DiT lacks a coarse-to-fine synthesis structure, making it unclear in which layers to perform the injection. Therefore, we propose an automatic method to identify "vital layers" within DiT, crucial for image formation, and demonstrate how these layers facilitate a range of controlled stable edits, from non-rigid modifications to object addition, using the same mechanism. Next, to enable real-image editing, we introduce an improved image inversion method for flow models. Finally, we evaluate our approach through qualitative and quantitative comparisons, along with a user study, and demonstrate its effectiveness across multiple applications. The project page is available at <a href="https://omriavrahami.com/stable-flow" rel="external noopener nofollow" class="link-external link-https">this https URL</a> </p> </div> </dd> <dt> <a name='item20'>[20]</a> <a href ="/abs/2411.16446" title="Abstract" id="2411.16446"> arXiv:2411.16446 </a> (replaced) [<a href="/pdf/2411.16446" title="Download PDF" id="pdf-2411.16446" aria-labelledby="pdf-2411.16446">pdf</a>, <a href="https://arxiv.org/html/2411.16446v2" title="View HTML" id="html-2411.16446" aria-labelledby="html-2411.16446" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2411.16446" title="Other formats" id="oth-2411.16446" aria-labelledby="oth-2411.16446">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> VQ-SGen: A Vector Quantized Stroke Representation for Creative Sketch Generation </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+J">Jiawei Wang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Cui,+Z">Zhiming Cui</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Li,+C">Changjian Li</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Graphics (cs.GR) </div> <p class='mathjax'> This paper presents VQ-SGen, a novel algorithm for high-quality creative sketch generation. Recent approaches have framed the task as pixel-based generation either as a whole or part-by-part, neglecting the intrinsic and contextual relationships among individual strokes, such as the shape and spatial positioning of both proximal and distant strokes. To overcome these limitations, we propose treating each stroke within a sketch as an entity and introducing a vector-quantized (VQ) stroke representation for fine-grained sketch generation. Our method follows a two-stage framework - in stage one, we decouple each stroke's shape and location information to ensure the VQ representation prioritizes stroke shape learning. In stage two, we feed the precise and compact representation into an auto-decoding Transformer to incorporate stroke semantics, positions, and shapes into the generation process. By utilizing tokenized stroke representation, our approach generates strokes with high fidelity and facilitates novel applications, such as text or class label conditioned generation and sketch completion. Comprehensive experiments demonstrate our method surpasses existing state-of-the-art techniques on the CreativeSketch dataset, underscoring its effectiveness. </p> </div> </dd> <dt> <a name='item21'>[21]</a> <a href ="/abs/2411.19921" title="Abstract" id="2411.19921"> arXiv:2411.19921 </a> (replaced) [<a href="/pdf/2411.19921" title="Download PDF" id="pdf-2411.19921" aria-labelledby="pdf-2411.19921">pdf</a>, <a href="https://arxiv.org/html/2411.19921v2" title="View HTML" id="html-2411.19921" aria-labelledby="html-2411.19921" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2411.19921" title="Other formats" id="oth-2411.19921" aria-labelledby="oth-2411.19921">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+W">Wenjia Wang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Pan,+L">Liang Pan</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Dou,+Z">Zhiyang Dou</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Mei,+J">Jidong Mei</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Liao,+Z">Zhouyingcheng Liao</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lou,+Y">Yuke Lou</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wu,+Y">Yifan Wu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Yang,+L">Lei Yang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+J">Jingbo Wang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Komura,+T">Taku Komura</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Graphics (cs.GR) </div> <p class='mathjax'> Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy, enabling more expressive and diverse human-scene interactions. Specifically, we employ Large Language Models with Retrieval-Augmented Generation (RAG) to generate coherent and diverse long-form scripts, providing a rich foundation for motion planning. A versatile multicondition physics-based control policy is also developed, which leverages text embeddings from the generated scripts to encode stylistic cues, simultaneously perceiving environmental geometries and accomplishing task goals. By integrating the retrieval-augmented script generation with the multi-condition controller, our approach provides a unified solution for generating stylized HSI motions. We further introduce a comprehensive planning dataset produced by RAG and a stylized motion dataset featuring diverse locomotions and interactions. Extensive experiments demonstrate SIMS's effectiveness in executing various tasks and generalizing across different scenarios, significantly outperforming previous methods. </p> </div> </dd> <dt> <a name='item22'>[22]</a> <a href ="/abs/2412.00259" title="Abstract" id="2412.00259"> arXiv:2412.00259 </a> (replaced) [<a href="/pdf/2412.00259" title="Download PDF" id="pdf-2412.00259" aria-labelledby="pdf-2412.00259">pdf</a>, <a href="https://arxiv.org/html/2412.00259v3" title="View HTML" id="html-2412.00259" aria-labelledby="html-2412.00259" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2412.00259" title="Other formats" id="oth-2412.00259" aria-labelledby="oth-2412.00259">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Rendering </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Zhu,+Y">Yifan Zhu</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Xiang,+T">Tianyi Xiang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Dollar,+A">Aaron Dollar</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Pan,+Z">Zherong Pan</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> 8 pages, 8 figures. Under review at Robotics Automation Letters </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Robotics (cs.RO)</span>; Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR) </div> <p class='mathjax'> Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments. However, existing methods that leverage differentiable programming to identify world models are incapable of jointly optimizing the geometry, appearance, and physical properties of the scene. In this work, we introduce a novel rigid object representation that allows the joint identification of these properties. Our method employs a novel differentiable point-based geometry representation coupled with a grid-based appearance field, which allows differentiable object collision detection and rendering. Combined with a differentiable physical simulator, we achieve end-to-end optimization of world models, given the sparse visual and tactile observations of a physical motion sequence. Through a series of world model identification tasks in simulated and real environments, we show that our method can learn both simulation- and rendering-ready world models from only one robot action sequence. </p> </div> </dd> <dt> <a name='item23'>[23]</a> <a href ="/abs/2412.04459" title="Abstract" id="2412.04459"> arXiv:2412.04459 </a> (replaced) [<a href="/pdf/2412.04459" title="Download PDF" id="pdf-2412.04459" aria-labelledby="pdf-2412.04459">pdf</a>, <a href="https://arxiv.org/html/2412.04459v3" title="View HTML" id="html-2412.04459" aria-labelledby="html-2412.04459" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2412.04459" title="Other formats" id="oth-2412.04459" aria-labelledby="oth-2412.04459">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Sun,+C">Cheng Sun</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Choe,+J">Jaesung Choe</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Loop,+C">Charles Loop</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Ma,+W">Wei-Chiu Ma</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+Y+F">Yu-Chiang Frank Wang</a></div> <div class='list-comments mathjax'><span class='descriptor'>Comments:</span> CVPR 2025; Project page at <a href="https://svraster.github.io/" rel="external noopener nofollow" class="link-external link-https">this https URL</a> ; Code at <a href="https://github.com/NVlabs/svraster" rel="external noopener nofollow" class="link-external link-https">this https URL</a> </div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Graphics (cs.GR) </div> <p class='mathjax'> We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The first is to adaptively and explicitly allocate sparse voxels to different levels of detail within scenes, faithfully reproducing scene details with $65536^3$ grid resolution while achieving high rendering frame rates. Second, we customize a rasterizer for efficient adaptive sparse voxels rendering. We render voxels in the correct depth order by using ray direction-dependent Morton ordering, which avoids the well-known popping artifact found in Gaussian splatting. Our method improves the previous neural-free voxel model by over 4db PSNR and more than 10x FPS speedup, achieving state-of-the-art comparable novel-view synthesis results. Additionally, our voxel representation is seamlessly compatible with grid-based 3D processing techniques such as Volume Fusion, Voxel Pooling, and Marching Cubes, enabling a wide range of future extensions and applications. </p> </div> </dd> <dt> <a name='item24'>[24]</a> <a href ="/abs/2502.03465" title="Abstract" id="2502.03465"> arXiv:2502.03465 </a> (replaced) [<a href="/pdf/2502.03465" title="Download PDF" id="pdf-2502.03465" aria-labelledby="pdf-2502.03465">pdf</a>, <a href="https://arxiv.org/html/2502.03465v2" title="View HTML" id="html-2502.03465" aria-labelledby="html-2502.03465" rel="noopener noreferrer" target="_blank">html</a>, <a href="/format/2502.03465" title="Other formats" id="oth-2502.03465" aria-labelledby="oth-2502.03465">other</a>] </dt> <dd> <div class='meta'> <div class='list-title mathjax'><span class='descriptor'>Title:</span> Seeing World Dynamics in a Nutshell </div> <div class='list-authors'><a href="https://arxiv.org/search/cs?searchtype=author&query=Shen,+Q">Qiuhong Shen</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Yi,+X">Xuanyu Yi</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Lin,+M">Mingbao Lin</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Zhang,+H">Hanwang Zhang</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Yan,+S">Shuicheng Yan</a>, <a href="https://arxiv.org/search/cs?searchtype=author&query=Wang,+X">Xinchao Wang</a></div> <div class='list-subjects'><span class='descriptor'>Subjects:</span> <span class="primary-subject">Computer Vision and Pattern Recognition (cs.CV)</span>; Artificial Intelligence (cs.AI); Graphics (cs.GR); Multimedia (cs.MM) </div> <p class='mathjax'> We consider the problem of efficiently representing casually captured monocular videos in a spatially- and temporally-coherent manner. While existing approaches predominantly rely on 2D/2.5D techniques treating videos as collections of spatiotemporal pixels, they struggle with complex motions, occlusions, and geometric consistency due to absence of temporal coherence and explicit 3D structure. Drawing inspiration from monocular video as a projection of the dynamic 3D world, we explore representing videos in their intrinsic 3D form through continuous flows of Gaussian primitives in space-time. In this paper, we propose NutWorld, a novel framework that efficiently transforms monocular videos into dynamic 3D Gaussian representations in a single forward pass. At its core, NutWorld introduces a structured spatial-temporal aligned Gaussian (STAG) representation, enabling optimization-free scene modeling with effective depth and flow regularization. Through comprehensive experiments, we demonstrate that NutWorld achieves high-fidelity video reconstruction quality while enabling various downstream applications in real-time. Demos and code will be available at <a href="https://github.com/Nut-World/NutWorld" rel="external noopener nofollow" class="link-external link-https">this https URL</a>. </p> </div> </dd> </dl> <div class='paging'>Total of 24 entries </div> <div class='morefewer'>Showing up to 2000 entries per page: <a href=/list/cs.GR/new?skip=0&show=1000 rel="nofollow"> fewer</a> | <span style="color: #454545">more</span> | <span style="color: #454545">all</span> </div> </div> </div> </div> </main> <footer style="clear: both;"> <div class="columns is-desktop" role="navigation" aria-label="Secondary" style="margin: -0.75em -0.75em 0.75em -0.75em">  <div class="column" style="padding: 0;"> <div class="columns"> <div class="column"> <ul style="list-style: none; line-height: 2;"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul style="list-style: none; line-height: 2;"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column" style="padding: 0;"> <div class="columns"> <div class="column"> <ul style="list-style: none; line-height: 2;"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul style="list-style: none; line-height: 2;"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>   </div> </footer> </div> <script src="/static/base/1.0.1/js/member_acknowledgement.js"></script> </body> </html>