Coarse-to-Fine Hyper-Prior Modeling for Learned Image Compression

Authors

  • Yueyu Hu Wangxuan Institute of Computer Technology, Peking University
  • Wenhan Yang Wangxuan Institute of Computer Technology, Peking University
  • Jiaying Liu Wangxuan Institute of Computer Technology, Peking University

DOI:

https://doi.org/10.1609/aaai.v34i07.6736

Abstract

Approaches to image compression with machine learning now achieve superior performance on the compression rate compared to existing hybrid codecs. The conventional learning-based methods for image compression exploits hyper-prior and spatial context model to facilitate probability estimations. Such models have limitations in modeling long-term dependency and do not fully squeeze out the spatial redundancy in images. In this paper, we propose a coarse-to-fine framework with hierarchical layers of hyper-priors to conduct comprehensive analysis of the image and more effectively reduce spatial redundancy, which improves the rate-distortion performance of image compression significantly. Signal Preserving Hyper Transforms are designed to achieve an in-depth analysis of the latent representation and the Information Aggregation Reconstruction sub-network is proposed to maximally utilize side-information for reconstruction. Experimental results show the effectiveness of the proposed network to efficiently reduce the redundancies in images and improve the rate-distortion performance, especially for high-resolution images. Our project is publicly available at https://huzi96.github.io/coarse-to-fine-compression.html.

Downloads

Published

2020-04-03

How to Cite

Hu, Y., Yang, W., & Liu, J. (2020). Coarse-to-Fine Hyper-Prior Modeling for Learned Image Compression. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11013-11020. https://doi.org/10.1609/aaai.v34i07.6736

Issue

Section

AAAI Technical Track: Vision