Neural Video Compression using GANs for Detail Synthesis and Propagation
This work addresses video compression quality for applications requiring high visual fidelity, representing a novel paradigm rather than an incremental improvement.
The authors tackled video compression by developing the first GAN-based neural method, which achieved superior visual quality in user studies compared to previous neural and non-neural approaches, though quantitative metrics failed to fully capture these improvements.
We present the first neural video compression method based on generative adversarial networks (GANs). Our approach significantly outperforms previous neural and non-neural video compression methods in a user study, setting a new state-of-the-art in visual quality for neural methods. We show that the GAN loss is crucial to obtain this high visual quality. Two components make the GAN loss effective: we i) synthesize detail by conditioning the generator on a latent extracted from the warped previous reconstruction to then ii) propagate this detail with high-quality flow. We find that user studies are required to compare methods, i.e., none of our quantitative metrics were able to predict all studies. We present the network design choices in detail, and ablate them with user studies.