RustNeRF: Robust Neural Radiance Field with Low-Quality Images
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913187776954368 |
|---|---|
| author | Li, Mengfei Lu, Ming Li, Xiaofang Zhang, Shanghang |
| author_facet | Li, Mengfei Lu, Ming Li, Xiaofang Zhang, Shanghang |
| contents | Recent work on Neural Radiance Fields (NeRF) exploits multi-view 3D consistency, achieving impressive results in 3D scene modeling and high-fidelity novel-view synthesis. However, there are limitations. First, existing methods assume enough high-quality images are available for training the NeRF model, ignoring real-world image degradation. Second, previous methods struggle with ambiguity in the training set due to unmodeled inconsistencies among different views. In this work, we present RustNeRF for real-world high-quality NeRF. To improve NeRF's robustness under real-world inputs, we train a 3D-aware preprocessing network that incorporates real-world degradation modeling. We propose a novel implicit multi-view guidance to address information loss during image degradation and restoration. Extensive experiments demonstrate RustNeRF's advantages over existing approaches under real-world degradation. The code will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03257 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RustNeRF: Robust Neural Radiance Field with Low-Quality Images Li, Mengfei Lu, Ming Li, Xiaofang Zhang, Shanghang Computer Vision and Pattern Recognition Graphics Recent work on Neural Radiance Fields (NeRF) exploits multi-view 3D consistency, achieving impressive results in 3D scene modeling and high-fidelity novel-view synthesis. However, there are limitations. First, existing methods assume enough high-quality images are available for training the NeRF model, ignoring real-world image degradation. Second, previous methods struggle with ambiguity in the training set due to unmodeled inconsistencies among different views. In this work, we present RustNeRF for real-world high-quality NeRF. To improve NeRF's robustness under real-world inputs, we train a 3D-aware preprocessing network that incorporates real-world degradation modeling. We propose a novel implicit multi-view guidance to address information loss during image degradation and restoration. Extensive experiments demonstrate RustNeRF's advantages over existing approaches under real-world degradation. The code will be released. |
| title | RustNeRF: Robust Neural Radiance Field with Low-Quality Images |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2401.03257 |