Deblur Gaussian Splatting SLAM
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912277310996480 |
|---|---|
| author | Girlanda, Francesco Rozumnyi, Denys Pollefeys, Marc Oswald, Martin R. |
| author_facet | Girlanda, Francesco Rozumnyi, Denys Pollefeys, Marc Oswald, Martin R. |
| contents | We present Deblur-SLAM, a robust RGB SLAM pipeline designed to recover sharp reconstructions from motion-blurred inputs. The proposed method bridges the strengths of both frame-to-frame and frame-to-model approaches to model sub-frame camera trajectories that lead to high-fidelity reconstructions in motion-blurred settings. Moreover, our pipeline incorporates techniques such as online loop closure and global bundle adjustment to achieve a dense and precise global trajectory. We model the physical image formation process of motion-blurred images and minimize the error between the observed blurry images and rendered blurry images obtained by averaging sharp virtual sub-frame images. Additionally, by utilizing a monocular depth estimator alongside the online deformation of Gaussians, we ensure precise mapping and enhanced image deblurring. The proposed SLAM pipeline integrates all these components to improve the results. We achieve state-of-the-art results for sharp map estimation and sub-frame trajectory recovery both on synthetic and real-world blurry input data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12572 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deblur Gaussian Splatting SLAM Girlanda, Francesco Rozumnyi, Denys Pollefeys, Marc Oswald, Martin R. Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning We present Deblur-SLAM, a robust RGB SLAM pipeline designed to recover sharp reconstructions from motion-blurred inputs. The proposed method bridges the strengths of both frame-to-frame and frame-to-model approaches to model sub-frame camera trajectories that lead to high-fidelity reconstructions in motion-blurred settings. Moreover, our pipeline incorporates techniques such as online loop closure and global bundle adjustment to achieve a dense and precise global trajectory. We model the physical image formation process of motion-blurred images and minimize the error between the observed blurry images and rendered blurry images obtained by averaging sharp virtual sub-frame images. Additionally, by utilizing a monocular depth estimator alongside the online deformation of Gaussians, we ensure precise mapping and enhanced image deblurring. The proposed SLAM pipeline integrates all these components to improve the results. We achieve state-of-the-art results for sharp map estimation and sub-frame trajectory recovery both on synthetic and real-world blurry input data. |
| title | Deblur Gaussian Splatting SLAM |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2503.12572 |