GSGTrack: Gaussian Splatting-Guided Object Pose Tracking from RGB Videos
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910725437390848 |
|---|---|
| author | Chen, Zhiyuan Lu, Fan Yu, Guo Li, Bin Qu, Sanqing Huang, Yuan Fu, Changhong Chen, Guang |
| author_facet | Chen, Zhiyuan Lu, Fan Yu, Guo Li, Bin Qu, Sanqing Huang, Yuan Fu, Changhong Chen, Guang |
| contents | Tracking the 6DoF pose of unknown objects in monocular RGB video sequences is crucial for robotic manipulation. However, existing approaches typically rely on accurate depth information, which is non-trivial to obtain in real-world scenarios. Although depth estimation algorithms can be employed, geometric inaccuracy can lead to failures in RGBD-based pose tracking methods. To address this challenge, we introduce GSGTrack, a novel RGB-based pose tracking framework that jointly optimizes geometry and pose. Specifically, we adopt 3D Gaussian Splatting to create an optimizable 3D representation, which is learned simultaneously with a graph-based geometry optimization to capture the object's appearance features and refine its geometry. However, the joint optimization process is susceptible to perturbations from noisy pose and geometry data. Thus, we propose an object silhouette loss to address the issue of pixel-wise loss being overly sensitive to pose noise during tracking. To mitigate the geometric ambiguities caused by inaccurate depth information, we propose a geometry-consistent image pair selection strategy, which filters out low-confidence pairs and ensures robust geometric optimization. Extensive experiments on the OnePose and HO3D datasets demonstrate the effectiveness of GSGTrack in both 6DoF pose tracking and object reconstruction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02267 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GSGTrack: Gaussian Splatting-Guided Object Pose Tracking from RGB Videos Chen, Zhiyuan Lu, Fan Yu, Guo Li, Bin Qu, Sanqing Huang, Yuan Fu, Changhong Chen, Guang Computer Vision and Pattern Recognition Robotics Tracking the 6DoF pose of unknown objects in monocular RGB video sequences is crucial for robotic manipulation. However, existing approaches typically rely on accurate depth information, which is non-trivial to obtain in real-world scenarios. Although depth estimation algorithms can be employed, geometric inaccuracy can lead to failures in RGBD-based pose tracking methods. To address this challenge, we introduce GSGTrack, a novel RGB-based pose tracking framework that jointly optimizes geometry and pose. Specifically, we adopt 3D Gaussian Splatting to create an optimizable 3D representation, which is learned simultaneously with a graph-based geometry optimization to capture the object's appearance features and refine its geometry. However, the joint optimization process is susceptible to perturbations from noisy pose and geometry data. Thus, we propose an object silhouette loss to address the issue of pixel-wise loss being overly sensitive to pose noise during tracking. To mitigate the geometric ambiguities caused by inaccurate depth information, we propose a geometry-consistent image pair selection strategy, which filters out low-confidence pairs and ensures robust geometric optimization. Extensive experiments on the OnePose and HO3D datasets demonstrate the effectiveness of GSGTrack in both 6DoF pose tracking and object reconstruction. |
| title | GSGTrack: Gaussian Splatting-Guided Object Pose Tracking from RGB Videos |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2412.02267 |