Video Quality Metric improvement using motion and spatial masking

Abstract: Objective video quality assessment is of great importance in video compression and other video processing applications. In today's encoders Peak Signal to Noise Ratio or Sum of Absolute Differences are often used, though these metrics have limited correlation to perceived quality. In this paper other block-based quality measures are evaluated with superior performance on compression distortion when evaluating correlation with Mean Opinion Scores. The major results are that Block-based Visual Information Fidelity with optical flow and intra-frame Gaussian weighting outperforms PSRN, VIF, and SSIM. Also, a block-based weighted Mean Squared Error method is proposed that performs better than PSRN and SSIM, however not VIF and BB-VIF, with the advantage of high locality, which is useful in video encoding. The previously mentioned weighting methods have not been evaluated with SSIM, which is proposed for further studies.