GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918163804848128 |
|---|---|
| author | Li, Junbo Yuan, Weimin Wang, Yinuo Zeng, Yue Shu, Shihao Meng, Cai Bai, Xiangzhi |
| author_facet | Li, Junbo Yuan, Weimin Wang, Yinuo Zeng, Yue Shu, Shihao Meng, Cai Bai, Xiangzhi |
| contents | Accurate 6D pose estimation of 3D objects is a fundamental task in computer vision, and current research typically predicts the 6D pose by establishing correspondences between 2D image features and 3D model features. However, these methods often face difficulties with textureless objects and varying illumination conditions. To overcome these limitations, we propose GS2POSE, a novel approach for 6D object pose estimation. GS2POSE formulates a pose regression algorithm inspired by the principles of Bundle Adjustment (BA). By leveraging Lie algebra, we extend the capabilities of 3DGS to develop a pose-differentiable rendering pipeline, which iteratively optimizes the pose by comparing the input image to the rendered image. Additionally, GS2POSE updates color parameters within the 3DGS model, enhancing its adaptability to changes in illumination. Compared to previous models, GS2POSE demonstrates accuracy improvements of 1.4\%, 2.8\% and 2.5\% on the T-LESS, LineMod-Occlusion and LineMod datasets, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16777 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation Li, Junbo Yuan, Weimin Wang, Yinuo Zeng, Yue Shu, Shihao Meng, Cai Bai, Xiangzhi Computer Vision and Pattern Recognition Accurate 6D pose estimation of 3D objects is a fundamental task in computer vision, and current research typically predicts the 6D pose by establishing correspondences between 2D image features and 3D model features. However, these methods often face difficulties with textureless objects and varying illumination conditions. To overcome these limitations, we propose GS2POSE, a novel approach for 6D object pose estimation. GS2POSE formulates a pose regression algorithm inspired by the principles of Bundle Adjustment (BA). By leveraging Lie algebra, we extend the capabilities of 3DGS to develop a pose-differentiable rendering pipeline, which iteratively optimizes the pose by comparing the input image to the rendered image. Additionally, GS2POSE updates color parameters within the 3DGS model, enhancing its adaptability to changes in illumination. Compared to previous models, GS2POSE demonstrates accuracy improvements of 1.4\%, 2.8\% and 2.5\% on the T-LESS, LineMod-Occlusion and LineMod datasets, respectively. |
| title | GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.16777 |