Recent trending on learning based video compression: A survey

• DOI: 10.1016/j.cogr.2021.08.003
• Publication Date: 2021-08-25T15:58:09Z
• Authors: Trinh Man Hoang; Jinjia Zhou
• Keywords: Codec

The increase of video content and resolution drive more exploration compression techniques recently. Meanwhile, learning-based is receiving much attention over the past few years because its adaptivity parallelable computation. Although several promising reports were introduced, there no breakthrough work that can further go out research area. In this work, we provide an up-to-date overview milestones. particular, idea recent works on modules for conventional codec adaption end-to-end are reported along with their advantages disadvantages. According to review, compare current standard like HEVC or VVC, from 3% 12% BD-rate reduction have been achieved integrated approaches while outperformed results perceptual quality structure similarity approaches. Furthermore, future suggestion provided based obstacles. We conclude that, a long-term benefit, computation complexity major problem needed be solved, especially decoder-end. Whereas rate-dependent generative designs optimistic low-complex efficient codec.