Litcius/Paper detail

Learned Video Compression With Efficient Temporal Context Learning

Dengchao Jin, Jianjun Lei, Bo Peng, Zhaoqing Pan, Li Li, Nam Ling

2023IEEE Transactions on Image Processing29 citationsDOI

Abstract

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.

Topics & Concepts

Computer scienceCodecData compressionArtificial intelligenceComputer visionMotion compensationReference frameContext modelVideo compression picture typesRedundancy (engineering)Pattern recognition (psychology)Video processingVideo trackingFrame (networking)TelecommunicationsObject (grammar)Operating systemComputer hardwareVideo Coding and Compression TechnologiesVideo Analysis and SummarizationAdvanced Data Compression Techniques
Learned Video Compression With Efficient Temporal Context Learning | Litcius