Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data

Gangtao Xin; Pingyi Fan

doi:10.1038/s41598-023-29068-z

Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data

Sci Rep. 2023 Feb 2;13(1):1958. doi: 10.1038/s41598-023-29068-z.

Authors

Gangtao Xin^{1

2}, Pingyi Fan^{3

4}

Affiliations

¹ The Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China.
² The Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China.
³ The Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China. fpy@tsinghua.edu.cn.
⁴ The Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China. fpy@tsinghua.edu.cn.

Abstract

With the advancement of intelligent vision algorithms and devices, image reprocessing and secondary propagation are becoming increasingly prevalent. A large number of similar images are being produced rapidly and widely, resulting in the homogeneity and similarity of images. Moreover, it brings new challenges to compression systems, which need to exploit the potential of deep features and side information of images. However, traditional methods are incompetent for this issue. Soft compression is a novel data-driven image coding algorithm with superior performance. Compared with existing paradigms, it has distinctive characteristics: from hard to soft, from pixels to shapes, and from fixed to random. Soft compression may hold promise for human-centric/data-centric intelligent systems, making them efficient and reliable and finding potential in the metaverse and digital twins, etc. In this paper, we present a comprehensive and practical analysis of soft compression, revealing the functional role of each component in the system.