Densely Connected Pyramid Dehazing Network

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

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Generative Adversarial Text to Image Synthesis
• NIPS 2016 Tutorial: Generative Adversarial Networks
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• Pyramid Scene Parsing Network
• An All-in-One Network for Dehazing and Beyond
• Context Encoding for Semantic Segmentation
• Gated Fusion Network for Single Image Dehazing
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Joint Transmission Map Estimation and Dehazing using Deep Networks

Cited by in corpus (15)

• Residual Dense Network for Image Super-Resolution
• FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
• Gated Fusion Network for Single Image Dehazing
• Improved Techniques for Learning to Dehaze and Beyond: A Collective Study
• Gated Context Aggregation Network for Image Dehazing and Deraining
• Residual-Guide Feature Fusion Network for Single Image Deraining
• Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
• Fundus2Angio: A Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography
• The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
• Contrastive Learning for Compact Single Image Dehazing
• PaloBoost: An Overfitting-robust TreeBoost with Out-of-Bag Sample Regularization Techniques
• SDIT: Scalable and Diverse Cross-domain Image Translation
• Image Demoireing with Learnable Bandpass Filters
• Bi-Semantic Reconstructing Generative Network for Zero-shot Learning
• Implicit Euler ODE Networks for Single-Image Dehazing