Joint Transmission Map Estimation and Dehazing using Deep Networks

Abstract

Single image haze removal is an extremely challenging problem due to its inherent ill-posed nature. Several prior-based and learning-based methods have been proposed in the literature to solve this problem and they have achieved superior results. However, most of the existing methods assume constant atmospheric light model and tend to follow a two-step procedure involving prior-based methods for estimating transmission map followed by calculation of dehazed image using the closed form solution. In this paper, we relax the constant atmospheric light assumption and propose a novel unified single image dehazing network that jointly estimates the transmission map and performs dehazing. In other words, our new approach provides an end-to-end learning framework, where the inherent transmission map and dehazed result are learned directly from the loss function. Extensive experiments on synthetic and real datasets with challenging hazy images demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods.

This paper has been accepted in IEEE-TCSVT

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Conditional Generative Adversarial Nets
• Semantic Foggy Scene Understanding with Synthetic Data
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• Residual Non-local Attention Networks for Image Restoration
• An All-in-One Network for Dehazing and Beyond
• Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
• Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation
• Identity Preserving Face Completion for Large Ocular Region Occlusion

Cited by in corpus (8)

• Semantic Foggy Scene Understanding with Synthetic Data
• Density-aware Single Image De-raining using a Multi-stream Dense Network
• Densely Connected Pyramid Dehazing Network
• Single Image Haze Removal using a Generative Adversarial Network
• High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks
• DR-Net: Transmission Steered Single Image Dehazing Network with Weakly Supervised Refinement
• Deep Variational Bayesian Modeling of Haze Degradation Process
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey