Deep Variational Bayesian Modeling of Haze Degradation Process

TL;DR

This paper introduces a variational Bayesian approach for single image dehazing that models uncertainties and key factors like transmission and atmospheric light, improving performance and flexibility over existing methods.

Contribution

It proposes a novel Bayesian framework that jointly models haze degradation factors with neural networks, enhancing dehazing accuracy and enabling seamless integration with existing models.

Findings

Improved dehazing performance across multiple datasets.

Joint modeling of transmission and haze factors boosts accuracy.

Framework is compatible with various existing dehazing networks.

Abstract

Relying on the representation power of neural networks, most recent works have often neglected several factors involved in haze degradation, such as transmission (the amount of light reaching an observer from a scene over distance) and atmospheric light. These factors are generally unknown, making dehazing problems ill-posed and creating inherent uncertainties. To account for such uncertainties and factors involved in haze degradation, we introduce a variational Bayesian framework for single image dehazing. We propose to take not only a clean image and but also transmission map as latent variables, the posterior distributions of which are parameterized by corresponding neural networks: dehazing and transmission networks, respectively. Based on a physical model for haze degradation, our variational Bayesian framework leads to a new objective function that encourages the cooperation between them, facilitating the joint training of and thereby boosting the performance of each other. In our framework, a dehazing network can estimate a clean image independently of a transmission map estimation during inference, introducing no overhead. Furthermore, our model-agnostic framework can be seamlessly incorporated with other existing dehazing networks, greatly enhancing the performance consistently across datasets and models.