Efficient Learned Wavelet Image and Video Coding

TL;DR

This paper improves learned wavelet image and video coding by integrating a parallelized context model, significantly speeding up decoding while maintaining near state-of-the-art compression performance.

Contribution

It introduces a parallelized context model into iWave++, drastically increasing decoding speed with minimal impact on compression quality.

Findings

Speedup factor of over 350 for image coding

Speedup factor of over 240 for video coding

Rate-distortion performance slightly worse by 1.5% and 1% respectively

Abstract

Learned wavelet image and video coding approaches provide an explainable framework with a latent space corresponding to a wavelet decomposition. The wavelet image coder iWave++ achieves state-of-the-art performance and has been employed for various compression tasks, including lossy as well as lossless image, video, and medical data compression. However, the approaches suffer from slow decoding speed due to the autoregressive context model used in iWave++. In this paper, we show how a parallelized context model can be integrated into the iWave++ framework. Our experimental results demonstrate a speedup factor of over 350 and 240 for image and video compression, respectively. At the same time, the rate-distortion performance in terms of Bj{\o}ntegaard delta bitrate is slightly worse by 1.5\% for image coding and 1\% for video coding. In addition, we analyze the learned wavelet decomposition by visualizing its subband impulse responses.