Compact 3D Gaussian Splatting For Dense Visual SLAM
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_ | 1866914561727135744 |
|---|---|
| author | Deng, Tianchen Nie, Chang Liu, Shuhong Wu, Wenhua Yang, Jianfei Yuan, Shenghai Liu, Jiuming Wang, Danwei Wang, Hesheng |
| author_facet | Deng, Tianchen Nie, Chang Liu, Shuhong Wu, Wenhua Yang, Jianfei Yuan, Shenghai Liu, Jiuming Wang, Danwei Wang, Hesheng |
| contents | Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are built on a tremendous number of redundant 3D Gaussian ellipsoids, leading to high memory and storage costs, and slow training speed. To address the limitation, we propose a compact 3D Gaussian Splatting SLAM system that reduces the number and the parameter size of Gaussian ellipsoids. A sliding window-based masking strategy is first proposed to reduce the redundant ellipsoids. Then we observe that the covariance matrix (geometry) of most 3D Gaussian ellipsoids are extremely similar, which motivates a novel geometry codebook to compress 3D Gaussian geometric attributes, i.e., the parameters. Robust and accurate pose estimation is achieved by a global bundle adjustment method with reprojection loss. Extensive experiments demonstrate that our method achieves faster training and rendering speed while maintaining the state-of-the-art (SOTA) quality of the scene representation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11247 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Compact 3D Gaussian Splatting For Dense Visual SLAM Deng, Tianchen Nie, Chang Liu, Shuhong Wu, Wenhua Yang, Jianfei Yuan, Shenghai Liu, Jiuming Wang, Danwei Wang, Hesheng Computer Vision and Pattern Recognition Robotics Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are built on a tremendous number of redundant 3D Gaussian ellipsoids, leading to high memory and storage costs, and slow training speed. To address the limitation, we propose a compact 3D Gaussian Splatting SLAM system that reduces the number and the parameter size of Gaussian ellipsoids. A sliding window-based masking strategy is first proposed to reduce the redundant ellipsoids. Then we observe that the covariance matrix (geometry) of most 3D Gaussian ellipsoids are extremely similar, which motivates a novel geometry codebook to compress 3D Gaussian geometric attributes, i.e., the parameters. Robust and accurate pose estimation is achieved by a global bundle adjustment method with reprojection loss. Extensive experiments demonstrate that our method achieves faster training and rendering speed while maintaining the state-of-the-art (SOTA) quality of the scene representation. |
| title | Compact 3D Gaussian Splatting For Dense Visual SLAM |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2403.11247 |