This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2606.04621\">MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.04688\">MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.20131\">TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.31777\">Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.16813\">QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.14594\">TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.13644\">Surflo: Consistent 3D Surface Flow Model with Global State</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code>@librarian-bot recommend</code></p>\n","updatedAt":"2026-07-02T01:49:10.148Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":372,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6785541772842407},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.30673","authors":[{"_id":"6a447bab41f04ae4d7ad970a","name":"Chunshi Wang","hidden":false},{"_id":"6a447bab41f04ae4d7ad970b","name":"Haohan Weng","hidden":false},{"_id":"6a447bab41f04ae4d7ad970c","name":"Junliang Ye","hidden":false},{"_id":"6a447bab41f04ae4d7ad970d","name":"Biwen Lei","hidden":false},{"_id":"6a447bab41f04ae4d7ad970e","name":"Yang Li","hidden":false},{"_id":"6a447bab41f04ae4d7ad970f","name":"Zibo Zhao","hidden":false},{"_id":"6a447bab41f04ae4d7ad9710","name":"Zeqiang Lai","hidden":false},{"_id":"6a447bab41f04ae4d7ad9711","name":"Kaiyi Zhang","hidden":false},{"_id":"6a447bab41f04ae4d7ad9712","name":"Yunhan Yang","hidden":false},{"_id":"6a447bab41f04ae4d7ad9713","name":"Zhuo Chen","hidden":false},{"_id":"6a447bab41f04ae4d7ad9714","name":"Chunchao Guo","hidden":false},{"_id":"6a447bab41f04ae4d7ad9715","name":"Yawei Luo","hidden":false}],"publishedAt":"2026-06-25T00:00:00.000Z","submittedOnDailyAt":"2026-07-01T00:00:00.000Z","title":"PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation","submittedOnDailyBy":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user","name":"taesiri"},"summary":"Autoregressive Transformers dominate high-quality mesh generation by producing artist-worthy topologies, yet their inherent sequential decoding induces substantial computational overhead, falling orders of magnitude slower than parallel generative models. On the other hand, while continuous diffusion and flow-matching methods support efficient parallel synthesis across a variety of domains, they cannot be directly applied to meshes: mesh connectivity is inherently discrete and incompatible with standard continuous noise injection and denoising operations. To resolve this fundamental incompatibility, we introduce a compact topology embedder that projects discrete mesh vertex positions and normals into continuous per-vertex embeddings, where the original discrete adjacency information can be faithfully recovered via spacetime distance thresholding. After pretraining and freezing this embedder, any raw mesh can be fully converted into a continuous per-vertex state space unifying position, normal, and implicit topological attributes. Built upon this novel continuous mesh representation, we present PolyFlow, a Transformer-based flow-matching framework that achieves fully parallel vertex state denoising conditioned on extracted point-cloud features. During inference, our model completes generation rapidly via an ODE solver, and supports explicit, precise control over output mesh resolution by directly specifying the target vertex count. Extensive evaluations on the Toys4K benchmark demonstrate that PolyFlow surpasses state-of-the-art autoregressive baselines in both Chamfer Distance and Hausdorff Distance.","upvotes":9,"discussionId":"6a447bac41f04ae4d7ad9716","ai_summary":"PolyFlow introduces a continuous mesh representation using a topology embedder and applies flow-matching with Transformers for parallel mesh generation, achieving faster inference and precise resolution control compared to autoregressive methods.","ai_keywords":["Autoregressive Transformers","diffusion models","flow-matching","mesh generation","topology embedder","continuous mesh representation","ODE solver","Chamfer Distance","Hausdorff Distance"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"6645f953c39288df638dbdd5","name":"Tencent-Hunyuan","fullname":"Tencent Hunyuan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d22496c58f969c152bcefd/woKSjt2wXvBNKussyYPsa.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"631c386bc73939ffc0716a37","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1662793811119-noauth.jpeg","isPro":false,"fullname":"SeongWan Kim","user":"idgmatrix","type":"user"},{"_id":"6683fc5344a65be1aab25dc0","avatarUrl":"/avatars/e13cde3f87b59e418838d702807df3b5.svg","isPro":false,"fullname":"hjkim","user":"hojie11","type":"user"},{"_id":"686fc1fb779dd387eb29a46b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/686fc1fb779dd387eb29a46b/jdBko2vuxOB9HGAoryMZS.jpeg","isPro":false,"fullname":"Chunshi Wang","user":"AiEson2","type":"user"},{"_id":"676d009c4464f476aa2079b3","avatarUrl":"/avatars/3886bc22ec5ba4423c11b2f76a1f425b.svg","isPro":false,"fullname":"zhu","user":"de233","type":"user"},{"_id":"67729bd019b02ba84e38c933","avatarUrl":"/avatars/dc052dd8aee231a52f55f131dc7ff21d.svg","isPro":false,"fullname":"cyber","user":"cyber-loafing","type":"user"},{"_id":"664c4b46ae011af8d12d5ce4","avatarUrl":"/avatars/445a1f26f969b0d9170d1d91a1407c93.svg","isPro":false,"fullname":"YYX","user":"Okuzaki","type":"user"},{"_id":"673eb8cafdb92b14b4115543","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/RQ7lDdNADNdqqgn6BIbu1.png","isPro":false,"fullname":"flareless","user":"flareless","type":"user"},{"_id":"6270324ebecab9e2dcf245de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6270324ebecab9e2dcf245de/cMbtWSasyNlYc9hvsEEzt.jpeg","isPro":false,"fullname":"Kye Gomez","user":"kye","type":"user"},{"_id":"60c8d264224e250fb0178f77","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c8d264224e250fb0178f77/i8fbkBVcoFeJRmkQ9kYAE.png","isPro":false,"fullname":"Adam Lee","user":"Abecid","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6645f953c39288df638dbdd5","name":"Tencent-Hunyuan","fullname":"Tencent Hunyuan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d22496c58f969c152bcefd/woKSjt2wXvBNKussyYPsa.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.30673.md","query":{}}">
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
Authors: ,
,
,
,
,
,
,
,
,
,
,
Abstract
PolyFlow introduces a continuous mesh representation using a topology embedder and applies flow-matching with Transformers for parallel mesh generation, achieving faster inference and precise resolution control compared to autoregressive methods.
Autoregressive Transformers dominate high-quality mesh generation by producing artist-worthy topologies, yet their inherent sequential decoding induces substantial computational overhead, falling orders of magnitude slower than parallel generative models. On the other hand, while continuous diffusion and flow-matching methods support efficient parallel synthesis across a variety of domains, they cannot be directly applied to meshes: mesh connectivity is inherently discrete and incompatible with standard continuous noise injection and denoising operations. To resolve this fundamental incompatibility, we introduce a compact topology embedder that projects discrete mesh vertex positions and normals into continuous per-vertex embeddings, where the original discrete adjacency information can be faithfully recovered via spacetime distance thresholding. After pretraining and freezing this embedder, any raw mesh can be fully converted into a continuous per-vertex state space unifying position, normal, and implicit topological attributes. Built upon this novel continuous mesh representation, we present PolyFlow, a Transformer-based flow-matching framework that achieves fully parallel vertex state denoising conditioned on extracted point-cloud features. During inference, our model completes generation rapidly via an ODE solver, and supports explicit, precise control over output mesh resolution by directly specifying the target vertex count. Extensive evaluations on the Toys4K benchmark demonstrate that PolyFlow surpasses state-of-the-art autoregressive baselines in both Chamfer Distance and Hausdorff Distance.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.30673 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.30673 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.30673 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.