UCI and Disney Research scientists develop AI-enhanced video compression model | Center for Machine Learning and Intelligent Systems

Assistant professor of computer Science Stephan Mandt photo: Steve Zylius/UCI

A new artificial intelligence-enhanced video compression model developed by computer scientists at the University of California, Irvine and Disney Research has demonstrated that deep learning can compete against established video compression technology.

Unveiling their work in December at the Conference on Neural Information Processing Systems in Vancouver, British Columbia, the UCI/Disney Research team members showed that their compressor – while still in an early phase – yielded less distortion and significantly smaller bits-per-pixel rates than classical coding-decoding algorithms such as H.265 when trained on specialized video content and achieved comparable results on downscaled, publicly available YouTube videos.