Image Restoration by Estimating Frequency Distribution of Local Patches
This addresses image quality degradation for users of compressed images, but it is incremental as it builds on existing frequency-domain methods without adversarial training.
The paper tackles image restoration from JPEG compression by treating it as a classification problem in the frequency domain, using cross-entropy loss to estimate frequency distributions, and shows effective restoration with more detailed high-frequency components for vivid images.
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.