Deep Generative Video Compression
This work addresses video compression for multimedia applications, but it is incremental as it builds on existing neural image compression methods.
The authors tackled video compression by proposing an end-to-end deep generative model based on variational autoencoders, achieving competitive results on generic videos and extreme compression on specialized content.
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling approach to compress temporal sequences with a focus on video. Our approach builds upon variational autoencoder (VAE) models for sequential data and combines them with recent work on neural image compression. The approach jointly learns to transform the original sequence into a lower-dimensional representation as well as to discretize and entropy code this representation according to predictions of the sequential VAE. Rate-distortion evaluations on small videos from public data sets with varying complexity and diversity show that our model yields competitive results when trained on generic video content. Extreme compression performance is achieved when training the model on specialized content.