Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video

TL;DR

This paper introduces a depth-centric learning framework that jointly improves dehazing and depth estimation in real-world hazy videos by leveraging the atmospheric scattering model and brightness consistency constraint.

Contribution

The novel framework integrates haze removal and depth estimation through shared networks and regularization, advancing state-of-the-art performance in real-world hazy video processing.

Findings

Outperforms existing methods in video dehazing and depth estimation

Effectively handles real-world hazy scenes

Utilizes dual discriminators for detail enhancement and artifact reduction

Abstract

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.