Learned image compression techniques have achieved considerable development in recent years. In this paper, we find that the performance bottleneck lies in the use of a single hyperprior decoder, in which case the ternary Gaussian model collapses to a binary one. To solve this, we propose to use three hyperprior decoders to separate the decoding process of the mixed parameters in discrete Gaussian mixture likelihoods, achieving more accurate parameters estimation. Experimental results demonstrate the proposed method optimized by MS-SSIM achieves on average 3.36% BD-rate reduction compared with state-of-the-art approach. The contribution of the proposed method to the coding time and FLOPs is negligible.
@article{arxiv.2111.00485,
title = {Learned Image Compression with Separate Hyperprior Decoders},
author = {Zhao Zan and Chao Liu and Heming Sun and Xiaoyang Zeng and Yibo Fan},
journal= {arXiv preprint arXiv:2111.00485},
year = {2021}
}
Comments
This paper has been accepted by IEEE Open Journal of Circuits and Systems