Congrats to Zhihao and Ming!
Very novel idea, and very solid work with SOTA performance!
Zhihao Duan, Ming Lu, Zhan Ma, and Fengqing Zhu, Lossy Image Compression with Hierarchical VAEs, accepted by WACV, Jan. 2023.
Abstract: Recent work 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 from ResNet VAEs, which are originally designed for data (image) distribution modeling, we redesign their latent variable model using a quantizationaware posterior and prior, enabling easy quantization and entropy coding for image compression. Along with improved neural network blocks, we present a powerful and efficient class of lossy image coders, outperforming 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 will be made publicly available