Towards Generative Video Compression
Fabian Mentzer, Eirikur Agustsson, Johannes Ballé, David C. Minnen, Nick Johnston, George D. Toderici · arXiv (Cornell University) · 2021
We present a neural video compression method based on generative adversarial networks (GANs) that outperforms previous neural video compression methods and is comparable to HEVC in a user study. We propose a technique to mitigate temporal error accumulation caused by recursive frame compression that uses randomized shifting and un-shifting, motivated by a spectral analysis. We present in detail the network design choices, their relative importance, and elaborate on the challenges of evaluating video compression methods in user studies.