DR-Net: Transmission Steered Single Image Dehazing Network with Weakly Supervised Refinement

TL;DR

DR-Net is a comprehensive deep learning framework for single image dehazing that predicts transmission, reconstructs images, and refines details, achieving superior robustness and quality over previous methods.

Contribution

It introduces a novel end-to-end deep network with weakly supervised refinement for improved dehazing performance and applicability.

Findings

Outperforms state-of-the-art methods on synthetic and real images

Demonstrates robustness and accuracy in diverse scenes

Enhances details and color in dehazed images

Abstract

Despite the recent progress in image dehazing, several problems remain largely unsolved such as robustness for varying scenes, the visual quality of reconstructed images, and effectiveness and flexibility for applications. To tackle these problems, we propose a new deep network architecture for single image dehazing called DR-Net. Our model consists of three main subnetworks: a transmission prediction network that predicts transmission map for the input image, a haze removal network that reconstructs latent image steered by the transmission map, and a refinement network that enhances the details and color properties of the dehazed result via weakly supervised learning. Compared to previous methods, our method advances in three aspects: (i) pure data-driven model; (ii) the end-to-end system; (iii) superior robustness, accuracy, and applicability. Extensive experiments demonstrate that our DR-Net outperforms the state-of-the-art methods on both synthetic and real images in qualitative and quantitative metrics. Additionally, the utility of DR-Net has been illustrated by its potential usage in several important computer vision tasks.