Loopy-SLAM: Dense Neural SLAM with Loop Closures
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_ | 1866914830393278464 |
|---|---|
| author | Liso, Lorenzo Sandström, Erik Yugay, Vladimir Van Gool, Luc Oswald, Martin R. |
| author_facet | Liso, Lorenzo Sandström, Erik Yugay, Vladimir Van Gool, Luc Oswald, Martin R. |
| contents | Neural RGBD SLAM techniques have shown promise in dense Simultaneous Localization And Mapping (SLAM), yet face challenges such as error accumulation during camera tracking resulting in distorted maps. In response, we introduce Loopy-SLAM that globally optimizes poses and the dense 3D model. We use frame-to-model tracking using a data-driven point-based submap generation method and trigger loop closures online by performing global place recognition. Robust pose graph optimization is used to rigidly align the local submaps. As our representation is point based, map corrections can be performed efficiently without the need to store the entire history of input frames used for mapping as typically required by methods employing a grid based mapping structure. Evaluation on the synthetic Replica and real-world TUM-RGBD and ScanNet datasets demonstrate competitive or superior performance in tracking, mapping, and rendering accuracy when compared to existing dense neural RGBD SLAM methods. Project page: notchla.github.io/Loopy-SLAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09944 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Loopy-SLAM: Dense Neural SLAM with Loop Closures Liso, Lorenzo Sandström, Erik Yugay, Vladimir Van Gool, Luc Oswald, Martin R. Computer Vision and Pattern Recognition Neural RGBD SLAM techniques have shown promise in dense Simultaneous Localization And Mapping (SLAM), yet face challenges such as error accumulation during camera tracking resulting in distorted maps. In response, we introduce Loopy-SLAM that globally optimizes poses and the dense 3D model. We use frame-to-model tracking using a data-driven point-based submap generation method and trigger loop closures online by performing global place recognition. Robust pose graph optimization is used to rigidly align the local submaps. As our representation is point based, map corrections can be performed efficiently without the need to store the entire history of input frames used for mapping as typically required by methods employing a grid based mapping structure. Evaluation on the synthetic Replica and real-world TUM-RGBD and ScanNet datasets demonstrate competitive or superior performance in tracking, mapping, and rendering accuracy when compared to existing dense neural RGBD SLAM methods. Project page: notchla.github.io/Loopy-SLAM. |
| title | Loopy-SLAM: Dense Neural SLAM with Loop Closures |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.09944 |