Image Restoration by Estimating Frequency Distribution of Local Patches

Jaeyoung Yoo, Sang-ho Lee, Nojun Kwak; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 6684-6692

Abstract


In this paper, we propose a method to solve the image restoration problem, which tries to restore the details of a corrupted image, especially due to the loss caused by JPEG compression. We have treated an image in the frequency domain to explicitly restore the frequency components lost during image compression. In doing so, the distribution in the frequency domain is learned using the cross entropy loss. Unlike recent approaches, we have reconstructed the details of an image without using the scheme of adversarial training. Rather, the image restoration problem is treated as a classification problem to determine the frequency coefficient for each frequency band in an image patch. In this paper, we show that the proposed method effectively restores a JPEG-compressed image with more detailed high frequency components, making the restored image more vivid.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Yoo_2018_CVPR,
author = {Yoo, Jaeyoung and Lee, Sang-ho and Kwak, Nojun},
title = {Image Restoration by Estimating Frequency Distribution of Local Patches},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}