This document is an expanded version of a one-page abstract originally presented at the 2024 Data Compression Conference. It describes our proposed method for the video track of the Challenge on Learned Image Compression (CLIC) 2024. Our scheme follows the typical hybrid coding framework with some novel techniques. Firstly, we adopt Spynet network to produce accurate motion vectors for motion estimation. Secondly, we introduce the context mining scheme with conditional frame coding to fully exploit the spatial-temporal information. As for the low target bitrates given by CLIC, we integrate spatial-temporal super-resolution modules to improve rate-distortion performance. Our team name is IMCLVC.
@article{arxiv.2401.13959,
title = {Conditional Neural Video Coding with Spatial-Temporal Super-Resolution},
author = {Henan Wang and Xiaohan Pan and Runsen Feng and Zongyu Guo and Zhibo Chen},
journal= {arXiv preprint arXiv:2401.13959},
year = {2024}
}
Comments
Accepted by the 2024 Data Compression Conference (DCC) for presentation as a poster