All-in-One Image Compression and Restoration

TL;DR

This paper introduces a unified image compression and restoration framework capable of handling various degradations, achieving superior rate-distortion performance, strong generalization, and higher efficiency compared to existing methods.

Contribution

A novel all-in-one framework that integrates image restoration into compression, effectively managing multiple degradations without prior knowledge.

Findings

Superior rate-distortion performance on degraded images

Strong generalization to real-world scenarios

Higher computational efficiency

Abstract

Visual images corrupted by various types and levels of degradations are commonly encountered in practical image compression. However, most existing image compression methods are tailored for clean images, therefore struggling to achieve satisfying results on these images. Joint compression and restoration methods typically focus on a single type of degradation and fail to address a variety of degradations in practice. To this end, we propose a unified framework for all-in-one image compression and restoration, which incorporates the image restoration capability against various degradations into the process of image compression. The key challenges involve distinguishing authentic image content from degradations, and flexibly eliminating various degradations without prior knowledge. Specifically, the proposed framework approaches these challenges from two perspectives: i.e., content information aggregation, and degradation representation aggregation. Extensive experiments demonstrate the following merits of our model: 1) superior rate-distortion (RD) performance on various degraded inputs while preserving the performance on clean data; 2) strong generalization ability to real-world and unseen scenarios; 3) higher computing efficiency over compared methods. Our code is available at https://github.com/ZeldaM1/All-in-one.