Video Compression Based on Spatio-Temporal Resolution Adaptation
Video Compression Based on Spatio-Temporal Resolution Adaptation
复制标题
DOI：
10.1109/tcsvt.2018.2878952
复制
发表时间：
2019-01
影响因子：
8.4
通讯作者：
Mariana Afonso;Fan Zhang;D. Bull
中科院分区：
文献类型：
--
作者：
Mariana Afonso;Fan Zhang;D. Bull
提出了一种基于时空分辨率自适应的视频压缩框架（ViSTRA），该框架基于量化分辨率决策，在编码过程中对输入视频进行时空动态重采样，并在解码端重构全分辨率视频。使用帧重复执行时间上采样，而卷积神经网络超分辨率模型用于空间分辨率上采样。ViSTRA已集成到高效视频编码参考软件（HM 16.14）中。通过国际挑战验证的实验结果显示出显着的改进，基于PSNR的BD速率增益为15%，基于主观视觉质量测试的平均MOS差异为0.5。
A video compression framework based on spatio-temporal resolution adaptation (ViSTRA) is proposed, which dynamically resamples the input video spatially and temporally during encoding, based on a quantisation-resolution decision, and reconstructs the full resolution video at the decoder. Temporal upsampling is performed using frame repetition, whereas a convolutional neural network super-resolution model is employed for spatial resolution upsampling. ViSTRA has been integrated into the high efficiency video coding reference software (HM 16.14). Experimental results verified via an international challenge show significant improvements, with BD-rate gains of 15% based on PSNR and an average MOS difference of 0.5 based on subjective visual quality tests.