PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908320762167296 |
|---|---|
| author | Liu, Minghua Uy, Mikaela Angelina Xiang, Donglai Su, Hao Fidler, Sanja Sharp, Nicholas Gao, Jun |
| author_facet | Liu, Minghua Uy, Mikaela Angelina Xiang, Donglai Su, Hao Fidler, Sanja Sharp, Nicholas Gao, Jun |
| contents | We propose PartField, a feedforward approach for learning part-based 3D features, which captures the general concept of parts and their hierarchy without relying on predefined templates or text-based names, and can be applied to open-world 3D shapes across various modalities. PartField requires only a 3D feedforward pass at inference time, significantly improving runtime and robustness compared to prior approaches. Our model is trained by distilling 2D and 3D part proposals from a mix of labeled datasets and image segmentations on large unsupervised datasets, via a contrastive learning formulation. It produces a continuous feature field which can be clustered to yield a hierarchical part decomposition. Comparisons show that PartField is up to 20% more accurate and often orders of magnitude faster than other recent class-agnostic part-segmentation methods. Beyond single-shape part decomposition, consistency in the learned field emerges across shapes, enabling tasks such as co-segmentation and correspondence, which we demonstrate in several applications of these general-purpose, hierarchical, and consistent 3D feature fields. Check our Webpage! https://research.nvidia.com/labs/toronto-ai/partfield-release/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11451 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond Liu, Minghua Uy, Mikaela Angelina Xiang, Donglai Su, Hao Fidler, Sanja Sharp, Nicholas Gao, Jun Computer Vision and Pattern Recognition We propose PartField, a feedforward approach for learning part-based 3D features, which captures the general concept of parts and their hierarchy without relying on predefined templates or text-based names, and can be applied to open-world 3D shapes across various modalities. PartField requires only a 3D feedforward pass at inference time, significantly improving runtime and robustness compared to prior approaches. Our model is trained by distilling 2D and 3D part proposals from a mix of labeled datasets and image segmentations on large unsupervised datasets, via a contrastive learning formulation. It produces a continuous feature field which can be clustered to yield a hierarchical part decomposition. Comparisons show that PartField is up to 20% more accurate and often orders of magnitude faster than other recent class-agnostic part-segmentation methods. Beyond single-shape part decomposition, consistency in the learned field emerges across shapes, enabling tasks such as co-segmentation and correspondence, which we demonstrate in several applications of these general-purpose, hierarchical, and consistent 3D feature fields. Check our Webpage! https://research.nvidia.com/labs/toronto-ai/partfield-release/ |
| title | PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.11451 |