High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913525853585408 |
|---|---|
| author | Sun, Shuo Mielle, Malcolm Lilienthal, Achim J. Magnusson, Martin |
| author_facet | Sun, Shuo Mielle, Malcolm Lilienthal, Achim J. Magnusson, Martin |
| contents | We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. To this end, we first propose a Gaussian densification strategy based on the rendering loss to map unobserved areas and refine reobserved areas. Second, we introduce extra regularization parameters to alleviate the forgetting problem in the continuous mapping problem, where parameters tend to overfit the latest frame and result in decreasing rendering quality for previous frames. Both mapping and tracking are performed with Gaussian parameters by minimizing re-rendering loss in a differentiable way. Compared to recent neural and concurrently developed gaussian splatting RGBD SLAM baselines, our method achieves state-of-the-art results on the synthetic dataset Replica and competitive results on the real-world dataset TUM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12535 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization Sun, Shuo Mielle, Malcolm Lilienthal, Achim J. Magnusson, Martin Robotics Computer Vision and Pattern Recognition We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. To this end, we first propose a Gaussian densification strategy based on the rendering loss to map unobserved areas and refine reobserved areas. Second, we introduce extra regularization parameters to alleviate the forgetting problem in the continuous mapping problem, where parameters tend to overfit the latest frame and result in decreasing rendering quality for previous frames. Both mapping and tracking are performed with Gaussian parameters by minimizing re-rendering loss in a differentiable way. Compared to recent neural and concurrently developed gaussian splatting RGBD SLAM baselines, our method achieves state-of-the-art results on the synthetic dataset Replica and competitive results on the real-world dataset TUM. |
| title | High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12535 |