CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911213033619456 |
|---|---|
| author | Ackermann, Jan Kulhanek, Jonas Cai, Shengqu Xu, Haofei Pollefeys, Marc Wetzstein, Gordon Guibas, Leonidas Peng, Songyou |
| author_facet | Ackermann, Jan Kulhanek, Jonas Cai, Shengqu Xu, Haofei Pollefeys, Marc Wetzstein, Gordon Guibas, Leonidas Peng, Songyou |
| contents | In dynamic 3D environments, accurately updating scene representations over time is crucial for applications in robotics, mixed reality, and embodied AI. As scenes evolve, efficient methods to incorporate changes are needed to maintain up-to-date, high-quality reconstructions without the computational overhead of re-optimizing the entire scene. This paper introduces CL-Splats, which incrementally updates Gaussian splatting-based 3D representations from sparse scene captures. CL-Splats integrates a robust change-detection module that segments updated and static components within the scene, enabling focused, local optimization that avoids unnecessary re-computation. Moreover, CL-Splats supports storing and recovering previous scene states, facilitating temporal segmentation and new scene-analysis applications. Our extensive experiments demonstrate that CL-Splats achieves efficient updates with improved reconstruction quality over the state-of-the-art. This establishes a robust foundation for future real-time adaptation in 3D scene reconstruction tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21117 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization Ackermann, Jan Kulhanek, Jonas Cai, Shengqu Xu, Haofei Pollefeys, Marc Wetzstein, Gordon Guibas, Leonidas Peng, Songyou Computer Vision and Pattern Recognition In dynamic 3D environments, accurately updating scene representations over time is crucial for applications in robotics, mixed reality, and embodied AI. As scenes evolve, efficient methods to incorporate changes are needed to maintain up-to-date, high-quality reconstructions without the computational overhead of re-optimizing the entire scene. This paper introduces CL-Splats, which incrementally updates Gaussian splatting-based 3D representations from sparse scene captures. CL-Splats integrates a robust change-detection module that segments updated and static components within the scene, enabling focused, local optimization that avoids unnecessary re-computation. Moreover, CL-Splats supports storing and recovering previous scene states, facilitating temporal segmentation and new scene-analysis applications. Our extensive experiments demonstrate that CL-Splats achieves efficient updates with improved reconstruction quality over the state-of-the-art. This establishes a robust foundation for future real-time adaptation in 3D scene reconstruction tasks. |
| title | CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.21117 |