Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2311.14262 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910837674868736 |
|---|---|
| author | Xue, Yuheng Chen, Nenglun Liu, Jun Sun, Wenyun |
| author_facet | Xue, Yuheng Chen, Nenglun Liu, Jun Sun, Wenyun |
| contents | Zero-shot 3D part segmentation is a challenging and fundamental task. In this work, we propose a novel pipeline, ZeroPS, which achieves high-quality knowledge transfer from 2D pretrained foundation models (FMs), SAM and GLIP, to 3D object point clouds. We aim to explore the natural relationship between multi-view correspondence and the FMs' prompt mechanism and build bridges on it. In ZeroPS, the relationship manifests as follows: 1) lifting 2D to 3D by leveraging co-viewed regions and SAM's prompt mechanism, 2) relating 1D classes to 3D parts by leveraging 2D-3D view projection and GLIP's prompt mechanism, and 3) enhancing prediction performance by leveraging multi-view observations. Extensive evaluations on the PartNetE and AKBSeg benchmarks demonstrate that ZeroPS significantly outperforms the SOTA method across zero-shot unlabeled and instance segmentation tasks. ZeroPS does not require additional training or fine-tuning for the FMs. ZeroPS applies to both simulated and real-world data. It is hardly affected by domain shift. The project page is available at https://luis2088.github.io/ZeroPS_page. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_14262 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation Xue, Yuheng Chen, Nenglun Liu, Jun Sun, Wenyun Computer Vision and Pattern Recognition Zero-shot 3D part segmentation is a challenging and fundamental task. In this work, we propose a novel pipeline, ZeroPS, which achieves high-quality knowledge transfer from 2D pretrained foundation models (FMs), SAM and GLIP, to 3D object point clouds. We aim to explore the natural relationship between multi-view correspondence and the FMs' prompt mechanism and build bridges on it. In ZeroPS, the relationship manifests as follows: 1) lifting 2D to 3D by leveraging co-viewed regions and SAM's prompt mechanism, 2) relating 1D classes to 3D parts by leveraging 2D-3D view projection and GLIP's prompt mechanism, and 3) enhancing prediction performance by leveraging multi-view observations. Extensive evaluations on the PartNetE and AKBSeg benchmarks demonstrate that ZeroPS significantly outperforms the SOTA method across zero-shot unlabeled and instance segmentation tasks. ZeroPS does not require additional training or fine-tuning for the FMs. ZeroPS applies to both simulated and real-world data. It is hardly affected by domain shift. The project page is available at https://luis2088.github.io/ZeroPS_page. |
| title | ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.14262 |