Deep Inter Prediction with Error-Corrected Auto-Regressive Network for Video Coding

Yuzhang Hu

doi:10.1145/3528173

Deep Inter Prediction with Error-Corrected Auto-Regressive Network for Video Coding

2023-01-23

3

PRE

AI

DOI：10.1145/3528173

原文求助

摘要

En 中文

Modern codecs remove temporal redundancy of a video via inter prediction, i.e., searching previously coded frames for similar blocks and storing motion vectors to save bit-rates. However, existing codecs adopt blocklevel motion estimation, where a block is regressed by reference blocks linearly and is doomed to fail to deal with non-linear motions. In this article, we generate virtual reference frames (VRFs) with previously reconstructed frames via deep networks to offer an additional candidate, which is not constrained to linear motion structure and further significantly improves coding efficiency. More specifically, we propose a novel deep Auto-Regressive Moving-Average (ARMA) model, Error-Corrected Auto-Regressive Network (ECARNet), equipped with the powers of the conventional statistic ARMA models and deep networks jointly for reference frame prediction. Similar to conventionalARMAmodels, the ECAR-Net consists of two stages: AutoRegression (AR) stage and Error-Correction (EC) stage, where the first part predicts the signal at the current time-step based on previously reconstructed frames, while the second one compensates for the output of the AR stage to obtain finer details. Different from the statistic AR models only focusing on short-term temporal dependency, the AR model of our ECAR-Net is further injected with the long-term dynamics mechanism, where long temporal information is utilized to help predict motions more accurately. Furthermore, ECAR-Net works in a configuration-adaptive way, i.e., using different dynamics and error definitions for the Low Delay B and Random Access configurations, which helps improve the adaptivity and generality in diverse coding scenarios. With the well-designed network, our method surpasses HEVC on average 5.0% and 6.6% BD-rate saving for the luma component under the Low Delay B and Random Access configurations and also obtains on average 1.54% BD-rate saving over VVC. Furthermore, ECAR-Net works in a configuration-adaptive way, i.e., using different dynamics and error definitions for the Low Delay B and Random Access configurations, which helps improve the adaptivity and generality in diverse coding scenarios.

Keyword:

High Efficient Video Coding (HEVC)

inter prediction

deep learning

virtual reference frame

Error-Corrected Auto-Regressive Network

Versatile Video Coding (VVC)

Deep Inter Prediction with Error-Corrected Auto-Regressive Network for Video Coding

摘要

期刊

机构

引用论文