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

Authors

  • Yujun Huang Tsinghua University Research Center of Artificial Intelligence, Peng Cheng Laboratory
  • Bin Chen Harbin Institute of Technology, Shenzhen Research Center of Artificial Intelligence, Peng Cheng Laboratory Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies
  • Shiyu Qin Harbin Institute of Technology, ShenZhen
  • Jiawei Li HUAWEI Machine Co., Ltd. DongGuan
  • Yaowei Wang Research Center of Artificial Intelligence, Peng Cheng Laboratory
  • Tao Dai Shenzhen University
  • Shu-Tao Xia Tsinghua Shenzhen International Graduate School, Tsinghua University Research Center of Artificial Intelligence, Peng Cheng Laboratory

DOI:

https://doi.org/10.1609/aaai.v37i4.25551

Keywords:

DMKM: Data Compression, ML: Other Foundations of Machine Learning

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 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 find 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.

Downloads

Published

2023-06-26

How to Cite

Huang, Y., Chen, B., Qin, S., Li, J., Wang, Y., Dai, T., & Xia, S.-T. (2023). Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4322-4329. https://doi.org/10.1609/aaai.v37i4.25551

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management