Learned Video Compression with Residual Prediction and Loop Filter

TL;DR

This paper introduces a learned video codec utilizing residual prediction and loop filtering networks, achieving about 10% BD-rate savings and faster coding speeds through a lightweight ResNet backbone.

Contribution

The paper presents a novel learned video compression framework with residual prediction and feature-aided loop filtering, improving efficiency and speed over previous methods.

Findings

Approximately 10% BD-rate reduction compared to prior learned codecs.

Faster coding speed due to lightweight ResNet backbone.

Effective residual redundancy elimination and quality enhancement.

Abstract

In this paper, we propose a learned video codec with a residual prediction network (RP-Net) and a feature-aided loop filter (LF-Net). For the RP-Net, we exploit the residual of previous multiple frames to further eliminate the redundancy of the current frame residual. For the LF-Net, the features from residual decoding network and the motion compensation network are used to aid the reconstruction quality. To reduce the complexity, a light ResNet structure is used as the backbone for both RP-Net and LF-Net. Experimental results illustrate that we can save about 10% BD-rate compared with previous learned video compression frameworks. Moreover, we can achieve faster coding speed due to the ResNet backbone. This project is available at https://github.com/chaoliu18/RPLVC.