PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data
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_ | 1866917294633910272 |
|---|---|
| author | Zhu, Zhe Wan, Le Xu, Rui Zhang, Yiheng Chen, Honghua Dou, Zhiyang Lin, Cheng Liu, Yuan Wei, Mingqiang |
| author_facet | Zhu, Zhe Wan, Le Xu, Rui Zhang, Yiheng Chen, Honghua Dou, Zhiyang Lin, Cheng Liu, Yuan Wei, Mingqiang |
| contents | Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer supervision from 2D foundation models, such as SAM, by lifting multi-view masks into 3D. However, this indirect paradigm fails to capture intrinsic geometry, leading to surface-only understanding, uncontrolled decomposition, and limited generalization. We present PartSAM, the first promptable part segmentation model trained natively on large-scale 3D data. Following the design philosophy of SAM, PartSAM employs an encoder-decoder architecture in which a triplane-based dual-branch encoder produces spatially structured tokens for scalable part-aware representation learning. To enable large-scale supervision, we further introduce a model-in-the-loop annotation pipeline that curates over five million 3D shape-part pairs from online assets, providing diverse and fine-grained labels. This combination of scalable architecture and diverse 3D data yields emergent open-world capabilities: with a single prompt, PartSAM achieves highly accurate part identification, and in a Segment-Every-Part mode, it automatically decomposes shapes into both surface and internal structures. Extensive experiments show that PartSAM outperforms state-of-the-art methods by large margins across multiple benchmarks, marking a decisive step toward foundation models for 3D part understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21965 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data Zhu, Zhe Wan, Le Xu, Rui Zhang, Yiheng Chen, Honghua Dou, Zhiyang Lin, Cheng Liu, Yuan Wei, Mingqiang Computer Vision and Pattern Recognition Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer supervision from 2D foundation models, such as SAM, by lifting multi-view masks into 3D. However, this indirect paradigm fails to capture intrinsic geometry, leading to surface-only understanding, uncontrolled decomposition, and limited generalization. We present PartSAM, the first promptable part segmentation model trained natively on large-scale 3D data. Following the design philosophy of SAM, PartSAM employs an encoder-decoder architecture in which a triplane-based dual-branch encoder produces spatially structured tokens for scalable part-aware representation learning. To enable large-scale supervision, we further introduce a model-in-the-loop annotation pipeline that curates over five million 3D shape-part pairs from online assets, providing diverse and fine-grained labels. This combination of scalable architecture and diverse 3D data yields emergent open-world capabilities: with a single prompt, PartSAM achieves highly accurate part identification, and in a Segment-Every-Part mode, it automatically decomposes shapes into both surface and internal structures. Extensive experiments show that PartSAM outperforms state-of-the-art methods by large margins across multiple benchmarks, marking a decisive step toward foundation models for 3D part understanding. |
| title | PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.21965 |