SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting
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_ | 1866914891720294400 |
|---|---|
| author | Sabour, Sara Goli, Lily Kopanas, George Matthews, Mark Lagun, Dmitry Guibas, Leonidas Jacobson, Alec Fleet, David J. Tagliasacchi, Andrea |
| author_facet | Sabour, Sara Goli, Lily Kopanas, George Matthews, Mark Lagun, Dmitry Guibas, Leonidas Jacobson, Alec Fleet, David J. Tagliasacchi, Andrea |
| contents | 3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications.However, current methods require highly controlled environments (no moving people or wind-blown elements, and consistent lighting) to meet the inter-view consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures. Additional results available at: https://spotlesssplats.github.io |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_20055 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting Sabour, Sara Goli, Lily Kopanas, George Matthews, Mark Lagun, Dmitry Guibas, Leonidas Jacobson, Alec Fleet, David J. Tagliasacchi, Andrea Computer Vision and Pattern Recognition Machine Learning 3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications.However, current methods require highly controlled environments (no moving people or wind-blown elements, and consistent lighting) to meet the inter-view consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures. Additional results available at: https://spotlesssplats.github.io |
| title | SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.20055 |