KPNDepth: Depth Estimation of Lane Images under Complex Rainy Environment
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912063625887744 |
|---|---|
| author | Shi, Zhengxu |
| author_facet | Shi, Zhengxu |
| contents | Recent advancements in deep neural networks have improved depth estimation in clear, daytime driving scenarios. However, existing methods struggle with rainy conditions due to rain streaks and fog, which distort depth estimation. This paper introduces a novel dual-layer convolutional kernel prediction network for lane depth estimation in rainy environments. It predicts two sets of kernels to mitigate depth loss and rain streak artifacts. To address the scarcity of real rainy lane data, an image synthesis algorithm, RCFLane, is presented, creating a synthetic dataset called RainKITTI. Experiments show the framework's effectiveness in complex rainy conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09964 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KPNDepth: Depth Estimation of Lane Images under Complex Rainy Environment Shi, Zhengxu Computer Vision and Pattern Recognition Recent advancements in deep neural networks have improved depth estimation in clear, daytime driving scenarios. However, existing methods struggle with rainy conditions due to rain streaks and fog, which distort depth estimation. This paper introduces a novel dual-layer convolutional kernel prediction network for lane depth estimation in rainy environments. It predicts two sets of kernels to mitigate depth loss and rain streak artifacts. To address the scarcity of real rainy lane data, an image synthesis algorithm, RCFLane, is presented, creating a synthetic dataset called RainKITTI. Experiments show the framework's effectiveness in complex rainy conditions. |
| title | KPNDepth: Depth Estimation of Lane Images under Complex Rainy Environment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.09964 |