Improving Multi-generation Robustness of Learned Image Compression

TL;DR

This paper addresses the issue of multi-generation loss in learned image compression by analyzing its causes and proposing solutions, enabling high-quality repeated encoding over many cycles.

Contribution

It identifies the sources of generative loss in successive image compression and introduces methods to significantly reduce this loss, improving LIC robustness.

Findings

LIC maintains high quality after 50 reencodings

Proposed solutions outperform existing methods in multi-generation scenarios

Achieves comparable performance to BPG in repeated encoding tests

Abstract

Benefit from flexible network designs and end-to-end joint optimization approach, learned image compression (LIC) has demonstrated excellent coding performance and practical feasibility in recent years. However, existing compression models suffer from serious multi-generation loss, which always occurs during image editing and transcoding. During the process of repeatedly encoding and decoding, the quality of the image will rapidly degrade, resulting in various types of distortion, which significantly limits the practical application of LIC. In this paper, a thorough analysis is carried out to determine the source of generative loss in successive image compression (SIC). We point out and solve the quantization drift problem that affects SIC, reversibility loss function as well as channel relaxation method are proposed to further reduce the generation loss. Experiments show that by using our proposed solutions, LIC can achieve comparable performance to the first compression of BPG even after 50 times reencoding without any change of the network structure.