Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing
This addresses the problem of image dehazing for computer vision applications, but it is incremental as it builds upon CycleGAN with minor enhancements.
The authors tackled single image dehazing without paired training data by enhancing CycleGAN with cycle-consistency and perceptual losses, achieving improved quantitative and qualitative results on datasets like NYU-Depth, I-HAZE, and O-HAZE.
In this paper, we present an end-to-end network, called Cycle-Dehaze, for single image dehazing problem, which does not require pairs of hazy and corresponding ground truth images for training. That is, we train the network by feeding clean and hazy images in an unpaired manner. Moreover, the proposed approach does not rely on estimation of the atmospheric scattering model parameters. Our method enhances CycleGAN formulation by combining cycle-consistency and perceptual losses in order to improve the quality of textural information recovery and generate visually better haze-free images. Typically, deep learning models for dehazing take low resolution images as input and produce low resolution outputs. However, in the NTIRE 2018 challenge on single image dehazing, high resolution images were provided. Therefore, we apply bicubic downscaling. After obtaining low-resolution outputs from the network, we utilize the Laplacian pyramid to upscale the output images to the original resolution. We conduct experiments on NYU-Depth, I-HAZE, and O-HAZE datasets. Extensive experiments demonstrate that the proposed approach improves CycleGAN method both quantitatively and qualitatively.