ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts
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_ | 1866909472340836352 |
|---|---|
| author | Pjetri, Aurel Caprasecca, Stefano Taccari, Leonardo Simoncini, Matteo Monteagudo, Henrique Piñeiro Walter, Wallace de Andrade, Douglas Coimbra Sambo, Francesco Bagdanov, Andrew David |
| author_facet | Pjetri, Aurel Caprasecca, Stefano Taccari, Leonardo Simoncini, Matteo Monteagudo, Henrique Piñeiro Walter, Wallace de Andrade, Douglas Coimbra Sambo, Francesco Bagdanov, Andrew David |
| contents | Monocular depth estimation is a critical task for autonomous driving and many other computer vision applications. While significant progress has been made in this field, the effects of viewpoint shifts on depth estimation models remain largely underexplored. This paper introduces a novel dataset and evaluation methodology to quantify the impact of different camera positions and orientations on monocular depth estimation performance. We propose a ground truth strategy based on homography estimation and object detection, eliminating the need for expensive LIDAR sensors. We collect a diverse dataset of road scenes from multiple viewpoints and use it to assess the robustness of a modern depth estimation model to geometric shifts. After assessing the validity of our strategy on a public dataset, we provide valuable insights into the limitations of current models and highlight the importance of considering viewpoint variations in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17851 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts Pjetri, Aurel Caprasecca, Stefano Taccari, Leonardo Simoncini, Matteo Monteagudo, Henrique Piñeiro Walter, Wallace de Andrade, Douglas Coimbra Sambo, Francesco Bagdanov, Andrew David Computer Vision and Pattern Recognition Monocular depth estimation is a critical task for autonomous driving and many other computer vision applications. While significant progress has been made in this field, the effects of viewpoint shifts on depth estimation models remain largely underexplored. This paper introduces a novel dataset and evaluation methodology to quantify the impact of different camera positions and orientations on monocular depth estimation performance. We propose a ground truth strategy based on homography estimation and object detection, eliminating the need for expensive LIDAR sensors. We collect a diverse dataset of road scenes from multiple viewpoints and use it to assess the robustness of a modern depth estimation model to geometric shifts. After assessing the validity of our strategy on a public dataset, we provide valuable insights into the limitations of current models and highlight the importance of considering viewpoint variations in real-world applications. |
| title | ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.17851 |