Timezone: »

Deep Generative Video Compression
Salvator Lombardo · JUN HAN · Christopher Schroers · Stephan Mandt

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #108

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.

Author Information

Salvator Lombardo (Disney Research)
JUN HAN (Dartmouth College)

I am a Ph.D. student in Computer Science at Dartmouth College.

Christopher Schroers (Disney Research|Studios)
Stephan Mandt (University of California, Irvine)

More from the Same Authors