Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913475904667648 |
|---|---|
| author | Ungermann, Paul Ettenhofer, Armin Nießner, Matthias Roessle, Barbara |
| author_facet | Ungermann, Paul Ettenhofer, Armin Nießner, Matthias Roessle, Barbara |
| contents | 3D Gaussian Splatting has shown impressive novel view synthesis results; nonetheless, it is vulnerable to dynamic objects polluting the input data of an otherwise static scene, so called distractors. Distractors have severe impact on the rendering quality as they get represented as view-dependent effects or result in floating artifacts. Our goal is to identify and ignore such distractors during the 3D Gaussian optimization to obtain a clean reconstruction. To this end, we take a self-supervised approach that looks at the image residuals during the optimization to determine areas that have likely been falsified by a distractor. In addition, we leverage a pretrained segmentation network to provide object awareness, enabling more accurate exclusion of distractors. This way, we obtain segmentation masks of distractors to effectively ignore them in the loss formulation. We demonstrate that our approach is robust to various distractors and strongly improves rendering quality on distractor-polluted scenes, improving PSNR by 1.86dB compared to 3D Gaussian Splatting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11697 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors Ungermann, Paul Ettenhofer, Armin Nießner, Matthias Roessle, Barbara Computer Vision and Pattern Recognition 3D Gaussian Splatting has shown impressive novel view synthesis results; nonetheless, it is vulnerable to dynamic objects polluting the input data of an otherwise static scene, so called distractors. Distractors have severe impact on the rendering quality as they get represented as view-dependent effects or result in floating artifacts. Our goal is to identify and ignore such distractors during the 3D Gaussian optimization to obtain a clean reconstruction. To this end, we take a self-supervised approach that looks at the image residuals during the optimization to determine areas that have likely been falsified by a distractor. In addition, we leverage a pretrained segmentation network to provide object awareness, enabling more accurate exclusion of distractors. This way, we obtain segmentation masks of distractors to effectively ignore them in the loss formulation. We demonstrate that our approach is robust to various distractors and strongly improves rendering quality on distractor-polluted scenes, improving PSNR by 1.86dB compared to 3D Gaussian Splatting. |
| title | Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.11697 |