Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction

TL;DR

This paper introduces a novel density-variational learning framework for single image dehazing that enhances robustness across varying haze densities by leveraging negative hazy images and a consistency-regularized approach.

Contribution

It proposes a Contrast-Assisted Reconstruction Loss and a consistency regularization framework to improve dehazing robustness under diverse haze conditions.

Findings

Outperforms state-of-the-art methods on synthetic datasets

Achieves superior results on real-world hazy images

Enhances robustness to varying haze densities

Abstract

Single image dehazing as a fundamental low-level vision task, is essential for the development of robust intelligent surveillance system. In this paper, we make an early effort to consider dehazing robustness under variational haze density, which is a realistic while under-studied problem in the research filed of singe image dehazing. To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios. Specifically, the dehazing network is optimized under the consistency-regularized framework with the proposed Contrast-Assisted Reconstruction Loss (CARL). The CARL can fully exploit the negative information to facilitate the traditional positive-orient dehazing objective function, by squeezing the dehazed image to its clean target from different directions. Meanwhile, the consistency regularization keeps consistent outputs given multi-level hazy images, thus improving the model robustness. Extensive experimental results on two synthetic and three real-world datasets demonstrate that our method significantly surpasses the state-of-the-art approaches.