LightDepth: Single-View Depth Self-Supervision from Illumination Decline
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916488782282752 |
|---|---|
| author | Rodríguez-Puigvert, Javier Batlle, Víctor M. Montiel, J. M. M. Martinez-Cantin, Ruben Fua, Pascal Tardós, Juan D. Civera, Javier |
| author_facet | Rodríguez-Puigvert, Javier Batlle, Víctor M. Montiel, J. M. M. Martinez-Cantin, Ruben Fua, Pascal Tardós, Juan D. Civera, Javier |
| contents | Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be obtained. In such cases, multi-view self-supervision and synthetic-to-real transfer serve as alternative approaches, however, with a considerable performance reduction in comparison to supervised case. Instead, we propose a single-view self-supervised method that achieves a performance similar to the supervised case. In some medical devices, such as endoscopes, the camera and light sources are co-located at a small distance from the target surfaces. Thus, we can exploit that, for any given albedo and surface orientation, pixel brightness is inversely proportional to the square of the distance to the surface, providing a strong single-view self-supervisory signal. In our experiments, our self-supervised models deliver accuracies comparable to those of fully supervised ones, while being applicable without depth ground-truth data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_10525 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | LightDepth: Single-View Depth Self-Supervision from Illumination Decline Rodríguez-Puigvert, Javier Batlle, Víctor M. Montiel, J. M. M. Martinez-Cantin, Ruben Fua, Pascal Tardós, Juan D. Civera, Javier Computer Vision and Pattern Recognition Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be obtained. In such cases, multi-view self-supervision and synthetic-to-real transfer serve as alternative approaches, however, with a considerable performance reduction in comparison to supervised case. Instead, we propose a single-view self-supervised method that achieves a performance similar to the supervised case. In some medical devices, such as endoscopes, the camera and light sources are co-located at a small distance from the target surfaces. Thus, we can exploit that, for any given albedo and surface orientation, pixel brightness is inversely proportional to the square of the distance to the surface, providing a strong single-view self-supervisory signal. In our experiments, our self-supervised models deliver accuracies comparable to those of fully supervised ones, while being applicable without depth ground-truth data. |
| title | LightDepth: Single-View Depth Self-Supervision from Illumination Decline |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2308.10525 |