Image Haze Removal By Adaptive CycleGAN
Authors:
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1122-1127
Abstract
We introduce our machine-learning method to remove the fog and haze in image. Our model is based on CycleGAN, an ingenious image-to-image translation model, which can be applied to de-hazing task. The datasets that we used for training and testing are creatd according to the atmospheric scattering model. With the change of the adversarial loss from cross-entropy loss to hinge loss, and the change of the reconstruction loss from MAE loss to perceptual loss, we improve the performance measure of SSIM value from 0.828 to 0.841 on the NYU dataset. With the Middlebury stereo datasets, we achieve an SSIM value of 0.811, which is significantly better than the baseline CycleGAN model.Keywords
This publication has 11 references indexed in Scilit:
- EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis2017
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Image Style Transfer Using Convolutional Neural Networks2016
- DehazeNet: An End-to-End System for Single Image Haze RemovalIEEE Transactions on Image Processing, 2016
- Learning Conditional Random Fields for Stereo2007
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- High-accuracy stereo depth maps using structured light2003
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- Support-vector networksMachine Learning, 1995