LCCM-VC: Learned Conditional Coding Modes for Video Compression

TL;DR

LCCM-VC introduces learned conditional coding modes using CANF to enhance video compression, achieving state-of-the-art results especially at high quality and bitrate ranges for streaming applications.

Contribution

The paper presents a novel learned conditional coding framework for video compression that outperforms existing learning-based methods, particularly in high-quality scenarios.

Findings

Achieves state-of-the-art results among learning-based video codecs.

Improves compression efficiency in high-quality/high-bitrate range.

Utilizes conditional augmented normalizing flows for better coding modes.

Abstract

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, learning-based video coding still has some ways to go. In this paper we present learned conditional coding modes for video coding (LCCM-VC), a video coding model that achieves state-of-the-art results among learning-based video coding methods. Our model utilizes conditional coding engines from the recent conditional augmented normalizing flows (CANF) pipeline, 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 at https://github.com/hadihdz/lccm_vc