Semantically Structured Image Compression via Irregular Group-Based Decoupling

TL;DR

This paper introduces a novel image compression framework that uses irregular group-based decoupling and a group-independent transform to reduce redundancy, improve visual quality, and support downstream tasks.

Contribution

It proposes a new irregular group-based image compression method with a group-independent transform, enhancing bitrate efficiency and reconstruction fidelity compared to prior rectangular region approaches.

Findings

Significant bitrate savings achieved.

Superior visual quality demonstrated.

Enhanced support for downstream intelligent tasks.

Abstract

Image compression techniques typically focus on compressing rectangular images for human consumption, however, resulting in transmitting redundant content for downstream applications. To overcome this limitation, some previous works propose to semantically structure the bitstream, which can meet specific application requirements by selective transmission and reconstruction. Nevertheless, they divide the input image into multiple rectangular regions according to semantics and ignore avoiding information interaction among them, causing waste of bitrate and distorted reconstruction of region boundaries. In this paper, we propose to decouple an image into multiple groups with irregular shapes based on a customized group mask and compress them independently. Our group mask describes the image at a finer granularity, enabling significant bitrate saving by reducing the transmission of redundant content. Moreover, to ensure the fidelity of selective reconstruction, this paper proposes the concept of group-independent transform that maintain the independence among distinct groups. And we instantiate it by the proposed Group-Independent Swin-Block (GI Swin-Block). Experimental results demonstrate that our framework structures the bitstream with negligible cost, and exhibits superior performance on both visual quality and intelligent task supporting.