AIVC: Artificial Intelligence based Video Codec
This addresses video compression efficiency for multimedia applications, but it is incremental as it builds on existing neural codec approaches.
The paper tackles video compression by introducing AIVC, an end-to-end neural video codec based on conditional autoencoders, achieving performance competitive with HEVC under established test conditions.
This paper introduces AIVC, an end-to-end neural video codec. It is based on two conditional autoencoders MNet and CNet, for motion compensation and coding. AIVC learns to compress videos using any coding configurations through a single end-to-end rate-distortion optimization. Furthermore, it offers performance competitive with the recent video coder HEVC under several established test conditions. A comprehensive ablation study is performed to evaluate the benefits of the different modules composing AIVC. The implementation is made available at https://orange-opensource.github.io/AIVC/.