English

Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation

Image and Video Processing 2022-08-03 v3 Computer Vision and Pattern Recognition

Abstract

With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention. Recently, learned image compression methods had exceeded their classical counterparts in terms of rate-distortion performance. However, continuous rate adaptation remains an open question. Some learned image compression methods use multiple networks for multiple rates, while others use one single model at the expense of computational complexity increase and performance degradation. In this paper, we propose a continuously rate adjustable learned image compression framework, Asymmetric Gained Variational Autoencoder (AG-VAE). AG-VAE utilizes a pair of gain units to achieve discrete rate adaptation in one single model with a negligible additional computation. Then, by using exponential interpolation, continuous rate adaptation is achieved without compromising performance. Besides, we propose the asymmetric Gaussian entropy model for more accurate entropy estimation. Exhaustive experiments show that our method achieves comparable quantitative performance with SOTA learned image compression methods and better qualitative performance than classical image codecs. In the ablation study, we confirm the usefulness and superiority of gain units and the asymmetric Gaussian entropy model.

Keywords

Cite

@article{arxiv.2003.02012,
  title  = {Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation},
  author = {Ze Cui and Jing Wang and Shangyin Gao and Bo Bai and Tiansheng Guo and Yihui Feng},
  journal= {arXiv preprint arXiv:2003.02012},
  year   = {2022}
}

Comments

Accepted by CVPR 2021

R2 v1 2026-06-23T14:03:32.675Z