Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain

TL;DR

This paper introduces a multi-scale feature domain patch matching technique for distributed image compression that leverages side information more effectively, leading to approximately 20% better compression rates than previous image domain methods.

Contribution

The paper proposes a novel multi-scale feature domain patch matching method that enhances the utilization of side information in distributed image compression.

Findings

Achieves about 20% improvement in compression rate over previous methods.

Effectively handles scale, shape, and illumination variances in side information.

Utilizes multi-scale features for more robust patch matching.

Abstract

Beyond achieving higher compression efficiency over classical image compression codecs, deep image compression is expected to be improved with additional side information, e.g., another image from a different perspective of the same scene. To better utilize the side information under the distributed compression scenario, the existing method (Ayzik and Avidan 2020) only implements patch matching at the image domain to solve the parallax problem caused by the difference in viewing points. However, the patch matching at the image domain is not robust to the variance of scale, shape, and illumination caused by the different viewing angles, and can not make full use of the rich texture information of the side information image. To resolve this issue, we propose Multi-Scale Feature Domain Patch Matching (MSFDPM) to fully utilizes side information at the decoder of the distributed image compression model. Specifically, MSFDPM consists of a side information feature extractor, a multi-scale feature domain patch matching module, and a multi-scale feature fusion network. Furthermore, we reuse inter-patch correlation from the shallow layer to accelerate the patch matching of the deep layer. Finally, we nd that our patch matching in a multi-scale feature domain further improves compression rate by about 20% compared with the patch matching method at image domain (Ayzik and Avidan 2020).