ViSTRA2: Video coding using spatial resolution and effective bit depth adaptation

We present a new video compression framework (ViSTRA2) which exploits adaptation of spatial resolution and effective bit depth, down-sampling these parameters at the encoder based on perceptual criteria, up-sampling decoder using deep convolution neural network. ViSTRA2 has been integrated with reference software both HEVC (HM 16.20) VVC (VTM 4.01), evaluated under Joint Video Exploration Team Common Test Conditions Random Access configuration. Our results show consistent significant gains against HM Bj{\o}negaard Delta measurements, average BD-rate savings 12.6% (PSNR) 19.5% (VMAF) over 5.5% 8.6% VTM.