EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913268000358400 |
|---|---|
| author | Song, Ziyang Zhu, Ruijie Wang, Chuxin Deng, Jiacheng He, Jianfeng Zhang, Tianzhu |
| author_facet | Song, Ziyang Zhu, Ruijie Wang, Chuxin Deng, Jiacheng He, Jianfeng Zhang, Tianzhu |
| contents | Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically trained and tested on standard datasets, overlooking the impact of various adverse conditions prevalent in real-world applications, such as rainy days. As a result, it is commonly observed that these methods struggle to handle these challenging scenarios. To address this issue, we present EC-Depth, a novel self-supervised two-stage framework to achieve a robust depth estimation. In the first stage, we propose depth consistency regularization to propagate reliable supervision from standard to challenging scenes. In the second stage, we adopt the Mean Teacher paradigm and propose a novel consistency-based pseudo-label filtering strategy to improve the quality of pseudo-labels, further improving both the accuracy and robustness of our model. Extensive experiments demonstrate that our method achieves accurate and consistent depth predictions in both standard and challenging scenarios, surpassing existing state-of-the-art methods on KITTI, KITTI-C, DrivingStereo, and NuScenes-Night benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_08044 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenes Song, Ziyang Zhu, Ruijie Wang, Chuxin Deng, Jiacheng He, Jianfeng Zhang, Tianzhu Computer Vision and Pattern Recognition Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically trained and tested on standard datasets, overlooking the impact of various adverse conditions prevalent in real-world applications, such as rainy days. As a result, it is commonly observed that these methods struggle to handle these challenging scenarios. To address this issue, we present EC-Depth, a novel self-supervised two-stage framework to achieve a robust depth estimation. In the first stage, we propose depth consistency regularization to propagate reliable supervision from standard to challenging scenes. In the second stage, we adopt the Mean Teacher paradigm and propose a novel consistency-based pseudo-label filtering strategy to improve the quality of pseudo-labels, further improving both the accuracy and robustness of our model. Extensive experiments demonstrate that our method achieves accurate and consistent depth predictions in both standard and challenging scenarios, surpassing existing state-of-the-art methods on KITTI, KITTI-C, DrivingStereo, and NuScenes-Night benchmarks. |
| title | EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.08044 |