Image noise detection in global illumination methods based on FRVM

Global illumination methods based on stochastic techniques provide photo-realistic images. However, they are prone to stochastic perceptual noise that can be reduced by increasing the number of paths as proved by Monte Carlo theory. The problem of finding the required number of paths in order to ensure that human observers cannot perceive any noise is still open. Until now, we do not know precisely which features are considered by the human visual system (HVS) for the evaluation of the image quality. This paper proposes a relevant model to predict which image highlights perceptual noise by using fast relevance vector machine (FRVM). This model can then be used in any progressive stochastic global illumination method in order to find the visual convergence threshold of different parts of any image. A comparative study of this model with experimental psycho-visual scores demonstrates the good consistency between these scores and the model quality measures. The proposed model has also been compared with SVM model and gives competitive performances.