English

Lossy Image Compression with Quantized Hierarchical VAEs

Image and Video Processing 2023-03-28 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective of generative modeling. Starting with ResNet VAEs, which are originally designed for data (image) distribution modeling, we redesign their latent variable model using a quantization-aware posterior and prior, enabling easy quantization and entropy coding at test time. Along with improved neural network architecture, we present a powerful and efficient model that outperforms previous methods on natural image lossy compression. Our model compresses images in a coarse-to-fine fashion and supports parallel encoding and decoding, leading to fast execution on GPUs. Code is available at https://github.com/duanzhiihao/lossy-vae.

Keywords

Cite

@article{arxiv.2208.13056,
  title  = {Lossy Image Compression with Quantized Hierarchical VAEs},
  author = {Zhihao Duan and Ming Lu and Zhan Ma and Fengqing Zhu},
  journal= {arXiv preprint arXiv:2208.13056},
  year   = {2023}
}

Comments

WACV 2023 Best Algorithms Paper Award, revised version

R2 v1 2026-06-25T02:01:44.769Z