Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929285708644352 |
|---|---|
| author | Yugay, Vladimir Li, Yue Gevers, Theo Oswald, Martin R. |
| author_facet | Yugay, Vladimir Li, Yue Gevers, Theo Oswald, Martin R. |
| contents | We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD videos. To this end, we propose a novel effective strategy for seeding new Gaussians for newly explored areas and their effective online optimization that is independent of the scene size and thus scalable to larger scenes. This is achieved by organizing the scene into sub-maps which are independently optimized and do not need to be kept in memory. We further accomplish frame-to-model camera tracking by minimizing photometric and geometric losses between the input and rendered frames. The Gaussian representation allows for high-quality photo-realistic real-time rendering of real-world scenes. Evaluation on synthetic and real-world datasets demonstrates competitive or superior performance in mapping, tracking, and rendering compared to existing neural dense SLAM methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_10070 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting Yugay, Vladimir Li, Yue Gevers, Theo Oswald, Martin R. Computer Vision and Pattern Recognition Robotics We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD videos. To this end, we propose a novel effective strategy for seeding new Gaussians for newly explored areas and their effective online optimization that is independent of the scene size and thus scalable to larger scenes. This is achieved by organizing the scene into sub-maps which are independently optimized and do not need to be kept in memory. We further accomplish frame-to-model camera tracking by minimizing photometric and geometric losses between the input and rendered frames. The Gaussian representation allows for high-quality photo-realistic real-time rendering of real-world scenes. Evaluation on synthetic and real-world datasets demonstrates competitive or superior performance in mapping, tracking, and rendering compared to existing neural dense SLAM methods. |
| title | Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2312.10070 |