OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918086490193920 |
|---|---|
| author | Yang, Yunhan Zhou, Yufan Guo, Yuan-Chen Zou, Zi-Xin Huang, Yukun Liu, Ying-Tian Xu, Hao Liang, Ding Cao, Yan-Pei Liu, Xihui |
| author_facet | Yang, Yunhan Zhou, Yufan Guo, Yuan-Chen Zou, Zi-Xin Huang, Yukun Liu, Ying-Tian Xu, Hao Liang, Ding Cao, Yan-Pei Liu, Xihui |
| contents | The creation of 3D assets with explicit, editable part structures is crucial for advancing interactive applications, yet most generative methods produce only monolithic shapes, limiting their utility. We introduce OmniPart, a novel framework for part-aware 3D object generation designed to achieve high semantic decoupling among components while maintaining robust structural cohesion. OmniPart uniquely decouples this complex task into two synergistic stages: (1) an autoregressive structure planning module generates a controllable, variable-length sequence of 3D part bounding boxes, critically guided by flexible 2D part masks that allow for intuitive control over part decomposition without requiring direct correspondences or semantic labels; and (2) a spatially-conditioned rectified flow model, efficiently adapted from a pre-trained holistic 3D generator, synthesizes all 3D parts simultaneously and consistently within the planned layout. Our approach supports user-defined part granularity, precise localization, and enables diverse downstream applications. Extensive experiments demonstrate that OmniPart achieves state-of-the-art performance, paving the way for more interpretable, editable, and versatile 3D content. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06165 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion Yang, Yunhan Zhou, Yufan Guo, Yuan-Chen Zou, Zi-Xin Huang, Yukun Liu, Ying-Tian Xu, Hao Liang, Ding Cao, Yan-Pei Liu, Xihui Computer Vision and Pattern Recognition The creation of 3D assets with explicit, editable part structures is crucial for advancing interactive applications, yet most generative methods produce only monolithic shapes, limiting their utility. We introduce OmniPart, a novel framework for part-aware 3D object generation designed to achieve high semantic decoupling among components while maintaining robust structural cohesion. OmniPart uniquely decouples this complex task into two synergistic stages: (1) an autoregressive structure planning module generates a controllable, variable-length sequence of 3D part bounding boxes, critically guided by flexible 2D part masks that allow for intuitive control over part decomposition without requiring direct correspondences or semantic labels; and (2) a spatially-conditioned rectified flow model, efficiently adapted from a pre-trained holistic 3D generator, synthesizes all 3D parts simultaneously and consistently within the planned layout. Our approach supports user-defined part granularity, precise localization, and enables diverse downstream applications. Extensive experiments demonstrate that OmniPart achieves state-of-the-art performance, paving the way for more interpretable, editable, and versatile 3D content. |
| title | OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.06165 |