Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

By Xiaosu Zhu, Jingkuan Song, Lianli Gao, Fengcai Zheng, Hengtao Shen. 2022

86 citations recorded by the source corpus.

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 inter-correlations 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, code books 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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Hossein Rahmani
2. Jun Liu
3. Zhihao Duan
4. Justin Yang
5. Li Xu
6. Bryan M. Williams
7. Haoxuan Qu
8. Zhan Ma

Citations in the corpus

• Recent Advances of Continual Learning in Computer Vision: An Overview (2021, positive): “They used selective memory retrieval, which is shown to be more effective compared to random retrieval in continual analogical reasoning.”
• Towards Backward-Compatible Continual Learning of Image Compression (2024, background): “J along with X~~{n within a dedicated memory buffer before the fine-tuning stage.”