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.
@article{arxiv.2507.06165,
title = {OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion},
author = {Yunhan Yang and Yufan Zhou and Yuan-Chen Guo and Zi-Xin Zou and Yukun Huang and Ying-Tian Liu and Hao Xu and Ding Liang and Yan-Pei Cao and Xihui Liu},
journal= {arXiv preprint arXiv:2507.06165},
year = {2025}
}