WaveOne

The algorithm learns what arbitrary information in frames is important and efficiently compresscompresses the less important information. Through their modelsmodel's joint compression of motion and residual information, WaveOne's model is able to achieve multi-flow representation with multiple layers of motion vector. And, through their model, WaveOne proposes a method for machine learning-based spatial rate control, allowing a single architecture to tune for different bitrates.

WaveOne is working on building a compression for digital media using machine learning and deep learning to create context-dependent solutions.

WaveOne has been building a new algorithm for video compression, learned end-to-end using deep learning. The key idea behind video compression is that consecutive frames in video are similar, and so it is advantageous to compress the difference each frame has with the previous one.

WaveOne is a digital media company that uses artificial intelligence to compress videos. It was founded in 2016 by Lubomir Bourdev and Oren Rippel. WaveOne is based in Mountain View, California.