Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.08772 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917049829163008 |
|---|---|
| author | Dong, Shaocong Ding, Lihe Chen, Xiao Li, Yaokun Wang, Yuxin Wang, Yucheng Wang, Qi Kim, Jaehyeok Gao, Chenjian Huang, Zhanpeng Wang, Zibin Xue, Tianfan Xu, Dan |
| author_facet | Dong, Shaocong Ding, Lihe Chen, Xiao Li, Yaokun Wang, Yuxin Wang, Yucheng Wang, Qi Kim, Jaehyeok Gao, Chenjian Huang, Zhanpeng Wang, Zibin Xue, Tianfan Xu, Dan |
| contents | Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1) Single-latent representations fail to capture complex multi-part geometries, causing detail degradation; (2) Holistic latent coding neglects part independence and interrelationships critical for compositional design; (3) Global conditioning mechanisms lack fine-grained controllability. Inspired by human 3D design workflows, we propose CoPart - a part-aware diffusion framework that decomposes 3D objects into contextual part latents for coherent multi-part generation. This paradigm offers three advantages: i) Reduces encoding complexity through part decomposition; ii) Enables explicit part relationship modeling; iii) Supports part-level conditioning. We further develop a mutual guidance strategy to fine-tune pre-trained diffusion models for joint part latent denoising, ensuring both geometric coherence and foundation model priors. To enable large-scale training, we construct Partverse - a novel 3D part dataset derived from Objaverse through automated mesh segmentation and human-verified annotations. Extensive experiments demonstrate CoPart's superior capabilities in part-level editing, articulated object generation, and scene composition with unprecedented controllability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08772 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From One to More: Contextual Part Latents for 3D Generation Dong, Shaocong Ding, Lihe Chen, Xiao Li, Yaokun Wang, Yuxin Wang, Yucheng Wang, Qi Kim, Jaehyeok Gao, Chenjian Huang, Zhanpeng Wang, Zibin Xue, Tianfan Xu, Dan Computer Vision and Pattern Recognition Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1) Single-latent representations fail to capture complex multi-part geometries, causing detail degradation; (2) Holistic latent coding neglects part independence and interrelationships critical for compositional design; (3) Global conditioning mechanisms lack fine-grained controllability. Inspired by human 3D design workflows, we propose CoPart - a part-aware diffusion framework that decomposes 3D objects into contextual part latents for coherent multi-part generation. This paradigm offers three advantages: i) Reduces encoding complexity through part decomposition; ii) Enables explicit part relationship modeling; iii) Supports part-level conditioning. We further develop a mutual guidance strategy to fine-tune pre-trained diffusion models for joint part latent denoising, ensuring both geometric coherence and foundation model priors. To enable large-scale training, we construct Partverse - a novel 3D part dataset derived from Objaverse through automated mesh segmentation and human-verified annotations. Extensive experiments demonstrate CoPart's superior capabilities in part-level editing, articulated object generation, and scene composition with unprecedented controllability. |
| title | From One to More: Contextual Part Latents for 3D Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.08772 |