Video Compression through Image Interpolation
arXiv:1804.06919
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 on 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, MPEG-4 Part 2, and performs on par with H.264.
arXiv commentProject page: https://chaoyuaw.github.io/vcii/
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Pixel Recurrent Neural Networks
- End-to-end Optimized Image Compression
- Generating Videos with Scene Dynamics
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Lossy Image Compression with Compressive Autoencoders
- Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
- Real-Time Adaptive Image Compression
- Video Frame Interpolation via Adaptive Separable Convolution
- Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks