Learned Video Compression With Efficient Temporal Context Learning

doi:10.1109/TIP.2023.3276333

Learned Video Compression With Efficient Temporal Context Learning

2023-01-01

6

PRE

AI

DOI：10.1109/TIP.2023.3276333

原文链接

原文求助

摘要

En 中文

In contrast to image compression, the key of video compression is to efficiently exploit the temporal context for reducing the inter-frame redundancy. Existing learned video compression methods generally rely on utilizing short-term temporal correlations or image-oriented codecs, which prevents further improvement of the coding performance. This paper proposed a novel temporal context-based video compression network (TCVC-Net) for improving the performance of learned video compression. Specifically, a global temporal reference aggregation (GTRA) module is proposed to obtain an accurate temporal reference for motion-compensated prediction by aggregating long-term temporal context. Furthermore, in order to efficiently compress the motion vector and residue, a temporal conditional codec (TCC) is proposed to preserve structural and detailed information by exploiting the multi-frequency components in temporal context. Experimental results show that the proposed TCVC-Net outperforms public state-of-the-art methods in terms of both PSNR and MS-SSIM metrics.

Keyword:

Image coding

Video compression

Transforms

Codecs

Quantization (signal)

Video coding

Motion compensation

Learned video compression

inter-frame prediction

long-term correspondence

temporal context learning

TCVC-Net

Learned Video Compression With Efficient Temporal Context Learning

摘要

期刊

机构