Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911848227405824 |
|---|---|
| author | Yang, Haolin Zhao, Chaoqiang Sheng, Lu Tang, Yang |
| author_facet | Yang, Haolin Zhao, Chaoqiang Sheng, Lu Tang, Yang |
| contents | Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the videos taken under complex lighting conditions. Even with domain adaptation or photometric loss repair, performance is still limited by the poor supervision of night images on trainable networks. In this paper, we propose a self-supervised nighttime monocular depth estimation method that does not use any night images during training. Our framework utilizes day images as a stable source for self-supervision and applies physical priors (e.g., wave optics, reflection model and read-shot noise model) to compensate for some key day-night differences. With day-to-night data distribution compensation, our framework can be trained in an efficient one-stage self-supervised manner. Though no nighttime images are considered during training, qualitative and quantitative results demonstrate that our method achieves SoTA depth estimating results on the challenging nuScenes-Night and RobotCar-Night compared with existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13854 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation Yang, Haolin Zhao, Chaoqiang Sheng, Lu Tang, Yang Computer Vision and Pattern Recognition Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the videos taken under complex lighting conditions. Even with domain adaptation or photometric loss repair, performance is still limited by the poor supervision of night images on trainable networks. In this paper, we propose a self-supervised nighttime monocular depth estimation method that does not use any night images during training. Our framework utilizes day images as a stable source for self-supervision and applies physical priors (e.g., wave optics, reflection model and read-shot noise model) to compensate for some key day-night differences. With day-to-night data distribution compensation, our framework can be trained in an efficient one-stage self-supervised manner. Though no nighttime images are considered during training, qualitative and quantitative results demonstrate that our method achieves SoTA depth estimating results on the challenging nuScenes-Night and RobotCar-Night compared with existing methods. |
| title | Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.13854 |