$\"teaser.jpg\"$

\n","updatedAt":"2025-09-15T06:06:03.653Z","author":{"_id":"6434f9bfdf32a2296635f88d","avatarUrl":"/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg","fullname":"Xinhao Yan","name":"HowieYan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.861798882484436},"editors":["HowieYan"],"editorAvatarUrls":["/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg"],"reactions":[],"isReport":false}},{"id":"68c7cfe773af4a90e42d7fe5","author":{"_id":"67828779d2361bf689dd071a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/JABXwlDyoNgvsGRg5wDvU.png","fullname":"Afshar","name":"ArminKenedi","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false},"createdAt":"2025-09-15T08:35:51.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Github? ","html":"

Github?

\n","updatedAt":"2025-09-15T08:35:51.108Z","author":{"_id":"67828779d2361bf689dd071a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/JABXwlDyoNgvsGRg5wDvU.png","fullname":"Afshar","name":"ArminKenedi","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.5945990085601807},"editors":["ArminKenedi"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/JABXwlDyoNgvsGRg5wDvU.png"],"reactions":[],"isReport":false},"replies":[{"id":"68d3b34b08d7fff048c91686","author":{"_id":"6434f9bfdf32a2296635f88d","avatarUrl":"/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg","fullname":"Xinhao Yan","name":"HowieYan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1},"createdAt":"2025-09-24T09:00:59.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"We will open-source the code soon. Here is the project homepage: https://yanxinhao.github.io/Projects/X-Part/","html":"

We will open-source the code soon. Here is the project homepage: https://yanxinhao.github.io/Projects/X-Part/

\n","updatedAt":"2025-09-24T09:00:59.203Z","author":{"_id":"6434f9bfdf32a2296635f88d","avatarUrl":"/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg","fullname":"Xinhao Yan","name":"HowieYan","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7747507095336914},"editors":["HowieYan"],"editorAvatarUrls":["/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg"],"reactions":[],"isReport":false,"parentCommentId":"68c7cfe773af4a90e42d7fe5"}}]},{"id":"68c8be8fe51aa2ca84f0f3f8","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":264},"createdAt":"2025-09-16T01:34:07.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [BANG: Dividing 3D Assets via Generative Exploded Dynamics](https://huggingface.co/papers/2507.21493) (2025)\n* [HierOctFusion: Multi-scale Octree-based 3D Shape Generation via Part-Whole-Hierarchy Message Passing](https://huggingface.co/papers/2508.11106) (2025)\n* [Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention](https://huggingface.co/papers/2507.17745) (2025)\n* [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://huggingface.co/papers/2508.09977) (2025)\n* [MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds](https://huggingface.co/papers/2508.14879) (2025)\n* [SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing](https://huggingface.co/papers/2509.05144) (2025)\n* [SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass](https://huggingface.co/papers/2508.15769) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

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: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-09-16T01:34:07.503Z","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":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7180833220481873},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2509.08643","authors":[{"_id":"68c23e6829b8ec9932cd0974","user":{"_id":"6434f9bfdf32a2296635f88d","avatarUrl":"/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg","isPro":false,"fullname":"Xinhao Yan","user":"HowieYan","type":"user"},"name":"Xinhao Yan","status":"claimed_verified","statusLastChangedAt":"2025-09-12T16:13:12.403Z","hidden":false},{"_id":"68c23e6829b8ec9932cd0975","name":"Jiachen Xu","hidden":false},{"_id":"68c23e6829b8ec9932cd0976","name":"Yang Li","hidden":false},{"_id":"68c23e6829b8ec9932cd0977","name":"Changfeng Ma","hidden":false},{"_id":"68c23e6829b8ec9932cd0978","name":"Yunhan Yang","hidden":false},{"_id":"68c23e6829b8ec9932cd0979","name":"Chunshi Wang","hidden":false},{"_id":"68c23e6829b8ec9932cd097a","name":"Zibo Zhao","hidden":false},{"_id":"68c23e6829b8ec9932cd097b","name":"Zeqiang Lai","hidden":false},{"_id":"68c23e6829b8ec9932cd097c","name":"Yunfei Zhao","hidden":false},{"_id":"68c23e6829b8ec9932cd097d","name":"Zhuo Chen","hidden":false},{"_id":"68c23e6829b8ec9932cd097e","name":"Chunchao Guo","hidden":false}],"publishedAt":"2025-09-10T14:37:02.000Z","submittedOnDailyAt":"2025-09-15T04:35:09.673Z","title":"X-Part: high fidelity and structure coherent shape decomposition","submittedOnDailyBy":{"_id":"6434f9bfdf32a2296635f88d","avatarUrl":"/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg","isPro":false,"fullname":"Xinhao Yan","user":"HowieYan","type":"user"},"summary":"Generating 3D shapes at part level is pivotal for downstream applications\nsuch as mesh retopology, UV mapping, and 3D printing. However, existing\npart-based generation methods often lack sufficient controllability and suffer\nfrom poor semantically meaningful decomposition. To this end, we introduce\nX-Part, a controllable generative model designed to decompose a holistic 3D\nobject into semantically meaningful and structurally coherent parts with high\ngeometric fidelity. X-Part exploits the bounding box as prompts for the part\ngeneration and injects point-wise semantic features for meaningful\ndecomposition. Furthermore, we design an editable pipeline for interactive part\ngeneration. Extensive experimental results show that X-Part achieves\nstate-of-the-art performance in part-level shape generation. This work\nestablishes a new paradigm for creating production-ready, editable, and\nstructurally sound 3D assets. Codes will be released for public research.","upvotes":25,"discussionId":"68c23e6829b8ec9932cd097f","projectPage":"https://yanxinhao.github.io/Projects/X-Part/","githubRepo":"https://github.com/Tencent-Hunyuan/Hunyuan3D-Part/tree/main?tab=readme-ov-file","ai_summary":"X-Part is a generative model that decomposes 3D objects into semantically meaningful parts with high fidelity, using bounding boxes and point-wise semantic features, and supports interactive editing.","ai_keywords":["generative model","part-level shape generation","bounding box","point-wise semantic features","interactive part generation"],"githubStars":194},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65c1d4f04f21259d9944593c","avatarUrl":"/avatars/355d84485da1032df3a692de6549fb7c.svg","isPro":false,"fullname":"yamaguchi","user":"yamaguchi1997","type":"user"},{"_id":"686fc1fb779dd387eb29a46b","avatarUrl":"/avatars/710c34ac3404426dac4cc6221e29dcdd.svg","isPro":false,"fullname":"Mike Green","user":"AiEson2","type":"user"},{"_id":"6434f9bfdf32a2296635f88d","avatarUrl":"/avatars/dc19ba1080b0b17a220d7e52bd514f13.svg","isPro":false,"fullname":"Xinhao Yan","user":"HowieYan","type":"user"},{"_id":"64b4eecf2fc8324fcb63b404","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64b4eecf2fc8324fcb63b404/zGYqYVB4-o-GBMybJ8CDA.png","isPro":false,"fullname":"Yunhan Yang","user":"yhyang-myron","type":"user"},{"_id":"684fa82634ea4a9c44c563ea","avatarUrl":"/avatars/4cdec2638ee9f354ae42c7f14a17707f.svg","isPro":false,"fullname":"Xu","user":"Channnn97","type":"user"},{"_id":"66fe2aadd5ede3018ab704bf","avatarUrl":"/avatars/46f2ae3717d1dfa5773d419e4dc9a891.svg","isPro":false,"fullname":"Changhangfeng MA","user":"murcherful","type":"user"},{"_id":"6863a000e7d0e009965a687b","avatarUrl":"/avatars/60e495c0a1ed9a2ede7a23e0209044c6.svg","isPro":false,"fullname":"yan","user":"xiruii","type":"user"},{"_id":"68c2b6f91be5880077735969","avatarUrl":"/avatars/edf23338b3e88547607607c48cf371d1.svg","isPro":false,"fullname":"Jingyu Gong","user":"gongjingyuair","type":"user"},{"_id":"6787a306fe076b7cbc501815","avatarUrl":"/avatars/8dfe7c61511c1ce78d5b2fe119e8562b.svg","isPro":false,"fullname":"js tang","user":"tjs9707","type":"user"},{"_id":"61585e723db5b9d8243ba044","avatarUrl":"/avatars/8fd55d402ce3d2cbf2c2a451489f8542.svg","isPro":false,"fullname":"Ibrahim.H","user":"bitsnaps","type":"user"},{"_id":"67828779d2361bf689dd071a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/JABXwlDyoNgvsGRg5wDvU.png","isPro":false,"fullname":"Afshar","user":"ArminKenedi","type":"user"},{"_id":"638f308fc4444c6ca870b60a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/638f308fc4444c6ca870b60a/Q11NK-8-JbiilJ-vk2LAR.png","isPro":true,"fullname":"Linoy Tsaban","user":"linoyts","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2509.08643

X-Part: high fidelity and structure coherent shape decomposition

Published on Sep 10

· Submitted by

Xinhao Yan on Sep 15

Upvote

Authors:

Xinhao Yan ,

Abstract

X-Part is a generative model that decomposes 3D objects into semantically meaningful parts with high fidelity, using bounding boxes and point-wise semantic features, and supports interactive editing.

AI-generated summary

Generating 3D shapes at part level is pivotal for downstream applications such as mesh retopology, UV mapping, and 3D printing. However, existing part-based generation methods often lack sufficient controllability and suffer from poor semantically meaningful decomposition. To this end, we introduce X-Part, a controllable generative model designed to decompose a holistic 3D object into semantically meaningful and structurally coherent parts with high geometric fidelity. X-Part exploits the bounding box as prompts for the part generation and injects point-wise semantic features for meaningful decomposition. Furthermore, we design an editable pipeline for interactive part generation. Extensive experimental results show that X-Part achieves state-of-the-art performance in part-level shape generation. This work establishes a new paradigm for creating production-ready, editable, and structurally sound 3D assets. Codes will be released for public research.