Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

Xiaosu Zhu1; Jingkuan Song1; Lianli Gao1; Feng Zheng2; Heng Tao Shen1

10.1109/CVPR52688.2022.01709

2022

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1063-6919

978-1-6654-6947-0

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

17591-17600

18-24 June 2022

New Orleans, LA, USA

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

IEEE COMPUTER SOC

Modeling latent variables with priors and hyperpriors is an essential problem in variational image compression. Formally, trade-off between rate and distortion is handled well if priors and hyperpriors precisely describe latent variables. Current practices only adopt univariate priors and process each variable individually. However, we find intercorrelations and intra-correlations exist when observing latent variables in a vectorized perspective. These findings reveal visual redundancies to improve rate-distortion performance and parallel processing ability to speed up compression. This encourages us to propose a novel vectorized prior. Specifically, a multivariate Gaussian mixture is proposed with means and covariances to be estimated. Then, a novel probabilistic vector quantization is utilized to effectively approximate means, and remaining covariances are further induced to a unified mixture and solved by cascaded estimation without context models involved. Furthermore, codebooks involved in quantization are extended to multi-codebooks for complexity reduction, which formulates an efficient compression procedure. Extensive experiments on benchmark datasets against state-of-the-art indicate our model has better rate-distortion performance and an impressive 3.18x compression speed up, giving us the ability to perform real-time, high-quality variational image compression in practice. Our source code is publicly available at https://github.com/xiaosu-zhu/McQuic.

Low-level vision Image and video synthesis and generation Representation learning

其他

英语

CPCI-S

National Natural Science Foundation of China["62020106008","62122018","61772116","61872064"] ; Sichuan Science and Technology Program[2019JDTD0005]

Computer Science ; Imaging Science & Photographic Technology

Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology

WOS:000870783003041

IEEE

1.Center for Future Media, University of Electronic Science and Technology of China
2.Southern University of Science and Technology

Xiaosu Zhu,Jingkuan Song,Lianli Gao,et al. Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2022:17591-17600.