Unsupervised Single Image Dehazing Using Dark Channel Prior Loss

Abstract

Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlying transformation between hazy and clear images. Due to inherent limitations in collecting matching clear and hazy images, these methods resort to training on synthetic data; constructed from indoor images and corresponding depth information. This may result in a possible domain shift when treating outdoor scenes. We propose a completely unsupervised method of training via minimization of the well-known, Dark Channel Prior (DCP) energy function. Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP. Although our "Deep DCP" technique can be regarded as a fast approximator of DCP, it actually improves its results significantly. This suggests an additional regularization obtained via the network and learning process. Experiments show that our method performs on par with large-scale supervised methods.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• DehazeNet: An End-to-End System for Single Image Haze Removal
• The Perception-Distortion Tradeoff
• Benchmarking Single Image Dehazing and Beyond

Cited by in corpus (9)

• Multi-Scale Single Image Dehazing Using Laplacian and Gaussian Pyramids
• Dual-Scale Single Image Dehazing Via Neural Augmentation
• FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images
• Deep-Energy: Unsupervised Training of Deep Neural Networks
• Rank-One Prior: Toward Real-Time Scene Recovery
• T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing
• Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze
• Model-Based Single Image Deep Dehazing
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey