fNeRF: High Quality Radiance Fields from Practical Cameras
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911919150989312 |
|---|---|
| author | Hua, Yi Lassner, Christoph Stoll, Carsten Matthews, Iain |
| author_facet | Hua, Yi Lassner, Christoph Stoll, Carsten Matthews, Iain |
| contents | In recent years, the development of Neural Radiance Fields has enabled a previously unseen level of photo-realistic 3D reconstruction of scenes and objects from multi-view camera data. However, previous methods use an oversimplified pinhole camera model resulting in defocus blur being `baked' into the reconstructed radiance field. We propose a modification to the ray casting that leverages the optics of lenses to enhance scene reconstruction in the presence of defocus blur. This allows us to improve the quality of radiance field reconstructions from the measurements of a practical camera with finite aperture. We show that the proposed model matches the defocus blur behavior of practical cameras more closely than pinhole models and other approximations of defocus blur models, particularly in the presence of partial occlusions. This allows us to achieve sharper reconstructions, improving the PSNR on validation of all-in-focus images, on both synthetic and real datasets, by up to 3 dB. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10633 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | fNeRF: High Quality Radiance Fields from Practical Cameras Hua, Yi Lassner, Christoph Stoll, Carsten Matthews, Iain Computer Vision and Pattern Recognition Graphics In recent years, the development of Neural Radiance Fields has enabled a previously unseen level of photo-realistic 3D reconstruction of scenes and objects from multi-view camera data. However, previous methods use an oversimplified pinhole camera model resulting in defocus blur being `baked' into the reconstructed radiance field. We propose a modification to the ray casting that leverages the optics of lenses to enhance scene reconstruction in the presence of defocus blur. This allows us to improve the quality of radiance field reconstructions from the measurements of a practical camera with finite aperture. We show that the proposed model matches the defocus blur behavior of practical cameras more closely than pinhole models and other approximations of defocus blur models, particularly in the presence of partial occlusions. This allows us to achieve sharper reconstructions, improving the PSNR on validation of all-in-focus images, on both synthetic and real datasets, by up to 3 dB. |
| title | fNeRF: High Quality Radiance Fields from Practical Cameras |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2406.10633 |