SAMPart3D, a scalable zero-shot 3D part segmentation framework that segments any 3D object into semantic parts at multiple granularities, without requiring predefined part label sets as text prompts. For scalability, we use text-agnostic vision foundation models to distill a 3D feature extraction backbone, allowing scaling to large unlabeled 3D datasets to learn rich 3D priors. For flexibility, we distill scale-conditioned part-aware 3D features for 3D part segmentation at multiple granularities.
The resulting 3D part segmentation can directly support various applications, including part material editing, part geometry editing, and click-based hierarchical segmentation.
PartObjaverse-Tiny, a 3D part segmentation dataset which provides detailed semantic-level and instance-level part annotations for 200 complex 3D objects.
If you use this work or find it helpful, please consider citing:
@article{yang2024sampart3d, author = {Yang, Yunhan and Huang, Yukun and Guo, Yuan-Chen and Lu, Liangjun and Wu, Xiaoyang and Edmund Y., Lam and Cao, Yan-Pei and Liu, Xihui}, title = {SAMPart3D: Segment Any Part in 3D Objects}, journal = {arXiv preprint arXiv:2411.07184}, year = {2024}, }