Optical Flow and Mode Selection for Learning-based Video Coding
This is an incremental improvement for video compression, potentially benefiting streaming and storage applications.
The paper tackles inter-frame video coding by introducing a dual-autoencoder method (MOFNet and CodecNet) that computes optical flow and mode selection, achieving performance on par with HEVC under CLIC20 P-frame conditions.
This paper introduces a new method for inter-frame coding based on two complementary autoencoders: MOFNet and CodecNet. MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection. The optical flow is used to perform a prediction of the frame to code. The coding mode selection enables competition between direct copy of the prediction or transmission through CodecNet. The proposed coding scheme is assessed under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding conditions, where it is shown to perform on par with the state-of-the-art video codec ITU/MPEG HEVC. Moreover, the possibility of copying the prediction enables to learn the optical flow in an end-to-end fashion i.e. without relying on pre-training and/or a dedicated loss term.