LCCM-VC: Learned Conditional Coding Modes for Video Compression

End-to-end learning-based video compression has made steady progress over the last several years. However, unlike learning-based image coding, which has already surpassed its handcrafted counterparts, the progress on learning-based video coding has been slower. In this paper, we present learned conditional coding modes for video coding (LCCM-VC), a video coding model that competes favorably against HEVC reference software implementation. Our model utilizes conditional – rather than residual – coding, and introduces additional coding modes to improve compression performance. The compression efficiency is especially good in the high-quality/high-bitrate range, which is important for broadcast and video-on-demand streaming applications. The implementation of LCCM-VC is available athttps://github.com/hadihdz/lccm_vc