No-reference quality assessment in global illumination algorithms based on SVM

Global illumination algorithms based on stochastically techniques provide photo-realistic images. However, they are prone to noise that can be reduced by increasing the number of paths as proved by Monte Carlo theory. The problem of finding the number of paths that are required in order to ensure that human observers cannot perceive any stochastic noise is still open. This paper proposes a no-reference quality assessment model based on noise quality indexes and support vector machine (SVM) in order to predict which image highlights perceptual noise. This model can then be used in stochastic global illumination algorithms in order to find the visual convergence threshold of different parts of any image. A comparative study of this model with human psycho-visual scores demonstrates the good consistency between these scores and the learning model quality measures.