A Neural Network Model of Spatial Distortion Sensitivity for Video Quality Estimation

Accurate estimation of visual quality as perceived by humans is crucial for modern multimedia systems and, given the evident ease for humans, a surprisingly difficult task for computers. Complexity considerations as imperative for real-time applications render this problem even more challenging. This paper studies the application of a neural network-based spatial model of distortion sensitivity to the quality prediction of spatio-temporal videos. We propose a simple yet effective adaptation of the loss function to cope with saturation effects in human quality ratings. This adaptation drastically decreases the number of iterations necessary for training networks to replicate psychophysical human responses. Our experimental results show significantly improved prediction performance of the spatio-temporal PSNR when compensated for spatial distortion sensitivity while maintaining the advantage of low complexity.