Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.09160 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915239920926720 |
|---|---|
| author | Wang, Qingyuan Song, Rui Li, Jiaojiao Cheng, Kerui Ferstl, David Hu, Yinlin |
| author_facet | Wang, Qingyuan Song, Rui Li, Jiaojiao Cheng, Kerui Ferstl, David Hu, Yinlin |
| contents | We introduce SCFlow2, a plug-and-play refinement framework for 6D object pose estimation. Most recent 6D object pose methods rely on refinement to get accurate results. However, most existing refinement methods either suffer from noises in establishing correspondences, or rely on retraining for novel objects. SCFlow2 is based on the SCFlow model designed for refinement with shape constraint, but formulates the additional depth as a regularization in the iteration via 3D scene flow for RGBD frames. The key design of SCFlow2 is an introduction of geometry constraints into the training of recurrent matching network, by combining the rigid-motion embeddings in 3D scene flow and 3D shape prior of the target. We train SCFlow2 on a combination of dataset Objaverse, GSO and ShapeNet, and evaluate on BOP datasets with novel objects. After using our method as a post-processing, most state-of-the-art methods produce significantly better results, without any retraining or fine-tuning. The source code is available at https://scflow2.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09160 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow Wang, Qingyuan Song, Rui Li, Jiaojiao Cheng, Kerui Ferstl, David Hu, Yinlin Computer Vision and Pattern Recognition We introduce SCFlow2, a plug-and-play refinement framework for 6D object pose estimation. Most recent 6D object pose methods rely on refinement to get accurate results. However, most existing refinement methods either suffer from noises in establishing correspondences, or rely on retraining for novel objects. SCFlow2 is based on the SCFlow model designed for refinement with shape constraint, but formulates the additional depth as a regularization in the iteration via 3D scene flow for RGBD frames. The key design of SCFlow2 is an introduction of geometry constraints into the training of recurrent matching network, by combining the rigid-motion embeddings in 3D scene flow and 3D shape prior of the target. We train SCFlow2 on a combination of dataset Objaverse, GSO and ShapeNet, and evaluate on BOP datasets with novel objects. After using our method as a post-processing, most state-of-the-art methods produce significantly better results, without any retraining or fine-tuning. The source code is available at https://scflow2.github.io. |
| title | SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.09160 |