Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond

TL;DR

This paper introduces a novel deep learning architecture that combines physical priors and data-driven methods for image dehazing, improving robustness and extending to related tasks like underwater enhancement and rain removal.

Contribution

It proposes a residual aggregation network that integrates prior knowledge and haze distribution data, bridging the gap between traditional and deep learning approaches for scene radiance estimation.

Findings

Effective in synthetic and real-world haze removal

Robust to different haze distributions

Extensible to underwater and rain removal tasks

Abstract

Single image dehazing is an important low-level vision task with many applications. Early researches have investigated different kinds of visual priors to address this problem. However, they may fail when their assumptions are not valid on specific images. Recent deep networks also achieve relatively good performance in this task. But unfortunately, due to the disappreciation of rich physical rules in hazes, large amounts of data are required for their training. More importantly, they may still fail when there exist completely different haze distributions in testing images. By considering the collaborations of these two perspectives, this paper designs a novel residual architecture to aggregate both prior (i.e., domain knowledge) and data (i.e., haze distribution) information to propagate transmissions for scene radiance estimation. We further present a variational energy based perspective to investigate the intrinsic propagation behavior of our aggregated deep model. In this way, we actually bridge the gap between prior driven models and data driven networks and leverage advantages but avoid limitations of previous dehazing approaches. A lightweight learning framework is proposed to train our propagation network. Finally, by introducing a taskaware image separation formulation with a flexible optimization scheme, we extend the proposed model for more challenging vision tasks, such as underwater image enhancement and single image rain removal. Experiments on both synthetic and realworld images demonstrate the effectiveness and efficiency of the proposed framework.