Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency
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_ | 1866911762874368000 |
|---|---|
| author | Ka, Woonghyun Lee, Jae Young Choi, Jaehyun Kim, Junmo |
| author_facet | Ka, Woonghyun Lee, Jae Young Choi, Jaehyun Kim, Junmo |
| contents | In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the learning-based stereo-confidence network is generally utilized to identify errors in the pseudo-depth maps to prevent transferring the errors. However, the learning-based stereo-confidence networks should be trained with ground truth (GT), which is not feasible in a self-supervised setting. In this paper, we propose a method to identify and filter errors in the pseudo-depth map using multiple disparity maps by checking their consistency without the need for GT and a training process. Experimental results show that the proposed method outperforms the previous methods and works well on various configurations by filtering out erroneous areas where the stereo-matching is vulnerable, especially such as textureless regions, occlusion boundaries, and reflective surfaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_12019 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency Ka, Woonghyun Lee, Jae Young Choi, Jaehyun Kim, Junmo Computer Vision and Pattern Recognition In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the learning-based stereo-confidence network is generally utilized to identify errors in the pseudo-depth maps to prevent transferring the errors. However, the learning-based stereo-confidence networks should be trained with ground truth (GT), which is not feasible in a self-supervised setting. In this paper, we propose a method to identify and filter errors in the pseudo-depth map using multiple disparity maps by checking their consistency without the need for GT and a training process. Experimental results show that the proposed method outperforms the previous methods and works well on various configurations by filtering out erroneous areas where the stereo-matching is vulnerable, especially such as textureless regions, occlusion boundaries, and reflective surfaces. |
| title | Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.12019 |