Densely Connected Pyramid Dehazing Network

TL;DR

This paper introduces DCPDN, an end-to-end deep learning model for image dehazing that integrates physics-based scattering models, dense feature connections, and adversarial training to improve dehazing quality.

Contribution

It presents a novel densely connected pyramid network that jointly learns transmission maps and dehazed images, incorporating a physics-based model and adversarial training for enhanced performance.

Findings

Significant improvement over state-of-the-art dehazing methods

Effective joint learning of transmission map and dehazed image

Demonstrated robustness through extensive ablation studies

Abstract

We propose a new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazing all together. The end-to-end learning is achieved by directly embedding the atmospheric scattering model into the network, thereby ensuring that the proposed method strictly follows the physics-driven scattering model for dehazing. Inspired by the dense network that can maximize the information flow along features from different levels, we propose a new edge-preserving densely connected encoder-decoder structure with multi-level pyramid pooling module for estimating the transmission map. This network is optimized using a newly introduced edge-preserving loss function. To further incorporate the mutual structural information between the estimated transmission map and the dehazed result, we propose a joint-discriminator based on generative adversarial network framework to decide whether the corresponding dehazed image and the estimated transmission map are real or fake. An ablation study is conducted to demonstrate the effectiveness of each module evaluated at both estimated transmission map and dehazed result. Extensive experiments demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods. Code will be made available at: https://github.com/hezhangsprinter