Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video
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_ | 1866929632591216640 |
|---|---|
| author | Fan, Junkai Wang, Kun Yan, Zhiqiang Chen, Xiang Gao, Shangbing Li, Jun Yang, Jian |
| author_facet | Fan, Junkai Wang, Kun Yan, Zhiqiang Chen, Xiang Gao, Shangbing Li, Jun Yang, Jian |
| contents | In this paper, we study the challenging problem of simultaneously removing haze and estimating depth from real monocular hazy videos. These tasks are inherently complementary: enhanced depth estimation improves dehazing via the atmospheric scattering model (ASM), while superior dehazing contributes to more accurate depth estimation through the brightness consistency constraint (BCC). To tackle these intertwined tasks, we propose a novel depth-centric learning framework that integrates the ASM model with the BCC constraint. Our key idea is that both ASM and BCC rely on a shared depth estimation network. This network simultaneously exploits adjacent dehazed frames to enhance depth estimation via BCC and uses the refined depth cues to more effectively remove haze through ASM. Additionally, we leverage a non-aligned clear video and its estimated depth to independently regularize the dehazing and depth estimation networks. This is achieved by designing two discriminator networks: $D_{MFIR}$ enhances high-frequency details in dehazed videos, and $D_{MDR}$ reduces the occurrence of black holes in low-texture regions. Extensive experiments demonstrate that the proposed method outperforms current state-of-the-art techniques in both video dehazing and depth estimation tasks, especially in real-world hazy scenes. Project page: https://fanjunkai1.github.io/projectpage/DCL/index.html. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11395 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video Fan, Junkai Wang, Kun Yan, Zhiqiang Chen, Xiang Gao, Shangbing Li, Jun Yang, Jian Computer Vision and Pattern Recognition In this paper, we study the challenging problem of simultaneously removing haze and estimating depth from real monocular hazy videos. These tasks are inherently complementary: enhanced depth estimation improves dehazing via the atmospheric scattering model (ASM), while superior dehazing contributes to more accurate depth estimation through the brightness consistency constraint (BCC). To tackle these intertwined tasks, we propose a novel depth-centric learning framework that integrates the ASM model with the BCC constraint. Our key idea is that both ASM and BCC rely on a shared depth estimation network. This network simultaneously exploits adjacent dehazed frames to enhance depth estimation via BCC and uses the refined depth cues to more effectively remove haze through ASM. Additionally, we leverage a non-aligned clear video and its estimated depth to independently regularize the dehazing and depth estimation networks. This is achieved by designing two discriminator networks: $D_{MFIR}$ enhances high-frequency details in dehazed videos, and $D_{MDR}$ reduces the occurrence of black holes in low-texture regions. Extensive experiments demonstrate that the proposed method outperforms current state-of-the-art techniques in both video dehazing and depth estimation tasks, especially in real-world hazy scenes. Project page: https://fanjunkai1.github.io/projectpage/DCL/index.html. |
| title | Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.11395 |