Code and dataset are available at <a href=\"https://github.com/1nnoh/HiFi-BRep\" rel=\"nofollow\">https://github.com/1nnoh/HiFi-BRep</a></p>\n","updatedAt":"2026-08-18T05:47:18.436Z","author":{"_id":"64258e73120a3ed32333319e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64258e73120a3ed32333319e/f1_eZ6slEoVq8Kn4WbQDC.png","fullname":"Junhao Hou","name":"1nnoh","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8294050097465515},"editors":["1nnoh"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64258e73120a3ed32333319e/f1_eZ6slEoVq8Kn4WbQDC.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.16485","authors":[{"_id":"6a83f134675db694db8cd606","name":"Junhao Hou","hidden":false},{"_id":"6a83f134675db694db8cd607","name":"Chenqi Luo","hidden":false},{"_id":"6a83f134675db694db8cd608","name":"Pufan Wang","hidden":false},{"_id":"6a83f134675db694db8cd609","name":"Jiaying Lu","hidden":false},{"_id":"6a83f134675db694db8cd60a","name":"Yusheng Liu","hidden":false},{"_id":"6a83f134675db694db8cd60b","name":"Feiwei Qin","hidden":false},{"_id":"6a83f134675db694db8cd60c","name":"Meie Fang","hidden":false},{"_id":"6a83f134675db694db8cd60d","name":"Kun Zhou","hidden":false}],"publishedAt":"2026-08-17T00:00:00.000Z","submittedOnDailyAt":"2026-08-18T00:00:00.000Z","title":"HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation","submittedOnDailyBy":{"_id":"64258e73120a3ed32333319e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64258e73120a3ed32333319e/f1_eZ6slEoVq8Kn4WbQDC.png","isPro":false,"fullname":"Junhao Hou","user":"1nnoh","type":"user","name":"1nnoh"},"summary":"Boundary representation (B-Rep) generation is a fundamental task in computer-aided design, yet the direct synthesis of high-fidelity and structurally valid B-Reps remains a major challenge. Existing deep generative methods suffer from two forms of brittleness: representation brittleness, caused by padding noise and feature contamination in the latent space, and generation brittleness, stemming from sequential error propagation and a train-inference mismatch due to non-differentiable validity enforcement. We propose HiFi-BRep, a novel framework that addresses these limitations through two synergistic contributions. First, a topology-aware encoder constructs a high-fidelity latent representation by eliminating padding via learnable queries and preventing feature contamination with topology-guided attention. Second, a single-stage decoder jointly predicts geometry and topology in parallel, embedding core manifold constraints as a differentiable learning objective. This design ensures mutual guidance between geometry and topology while avoiding cascaded errors. Extensive experiments show that HiFi-BRep significantly outperforms state-of-the-art methods in both structural validity and geometric fidelity, providing a robust solution for high-quality B-Rep synthesis. Code and models are publicly available at https://github.com/1nnoh/HiFi-BRep.","upvotes":0,"discussionId":"6a83f134675db694db8cd60e","ai_summary":"HiFi-BRep improves B-Rep synthesis by using a topology-aware encoder and a single-stage decoder that jointly predicts geometry and topology with differentiable validity constraints.","ai_keywords":["boundary representation","B-Rep","topology-aware encoder","learnable queries","topology-guided attention","single-stage decoder","manifold constraints","differentiable learning objective"],"ai_summary_model":"thinkingmachines/Inkling-Small","organization":{"_id":"61bac2af530e5c78d7b99667","name":"zju","fullname":"Zhejiang University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/5e1058e9fcf41d740b69966d/7G1xjlxwCdMEmKcxNR0n5.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"organization":{"_id":"61bac2af530e5c78d7b99667","name":"zju","fullname":"Zhejiang University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/5e1058e9fcf41d740b69966d/7G1xjlxwCdMEmKcxNR0n5.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.16485.md","query":{}}">
HiFi-BRep: High-Fidelity Latent Representation for Robust B-Rep Generation
Abstract
HiFi-BRep improves B-Rep synthesis by using a topology-aware encoder and a single-stage decoder that jointly predicts geometry and topology with differentiable validity constraints.
Boundary representation (B-Rep) generation is a fundamental task in computer-aided design, yet the direct synthesis of high-fidelity and structurally valid B-Reps remains a major challenge. Existing deep generative methods suffer from two forms of brittleness: representation brittleness, caused by padding noise and feature contamination in the latent space, and generation brittleness, stemming from sequential error propagation and a train-inference mismatch due to non-differentiable validity enforcement. We propose HiFi-BRep, a novel framework that addresses these limitations through two synergistic contributions. First, a topology-aware encoder constructs a high-fidelity latent representation by eliminating padding via learnable queries and preventing feature contamination with topology-guided attention. Second, a single-stage decoder jointly predicts geometry and topology in parallel, embedding core manifold constraints as a differentiable learning objective. This design ensures mutual guidance between geometry and topology while avoiding cascaded errors. Extensive experiments show that HiFi-BRep significantly outperforms state-of-the-art methods in both structural validity and geometric fidelity, providing a robust solution for high-quality B-Rep synthesis. Code and models are publicly available at https://github.com/1nnoh/HiFi-BRep.
Community
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/2608.16485 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.16485 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.