Video Compression through Image Interpolation

Chao-Yuan Wu
Nayan Singhal
Philipp Krähenbühl

The University of Texas at Austin




MPEG-4 Part 2
(MS-SSIM=0.946)
H.264
(MS-SSIM=0.980)
Ours
(MS-SSIM=0.984)

Abstract

An ever increasing amount of our digital communication, media consumption, and content creation revolves around videos. We share, watch, and archive many aspects of our lives through them, all of which are powered by strong video compression. Traditional video compression is laboriously hand designed and hand optimized. This paper presents an alternative in an end-to-end deep learning codec. Our codec builds one simple idea: Video compression is repeated image interpolation. It thus benefits from recent advances in deep image interpolation and generation. Our deep video codec outperforms today's prevailing codecs, such as H.261, MPEG4 Part 2, and performs on par with H.264.



Paper


Additional results: [frames] [videos]