# Deep Generative Adversarial Compression Artifact Removal

## TL;DR

This paper introduces a GAN-based deep learning model for removing compression artifacts from images, improving visual quality and object detection performance on degraded images.

## Contribution

It presents a novel fully convolutional residual network trained with a generative adversarial framework for artifact removal, outperforming traditional loss functions.

## Key findings

- GAN produces more photorealistic images than MSE or SSIM.
- The model improves object detection accuracy on compressed images.
- The approach can serve as a pre-processing step for computer vision tasks.

## Abstract

Compression artifacts arise in images whenever a lossy compression algorithm is applied. These artifacts eliminate details present in the original image, or add noise and small structures; because of these effects they make images less pleasant for the human eye, and may also lead to decreased performance of computer vision algorithms such as object detectors. To eliminate such artifacts, when decompressing an image, it is required to recover the original image from a disturbed version. To this end, we present a feed-forward fully convolutional residual network model trained using a generative adversarial framework. To provide a baseline, we show that our model can be also trained optimizing the Structural Similarity (SSIM), which is a better loss with respect to the simpler Mean Squared Error (MSE). Our GAN is able to produce images with more photorealistic details than MSE or SSIM based networks. Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail. In this task, our GAN method obtains better performance than MSE or SSIM trained networks.