Reduced Reference Mesh Visual Quality Assessment Based on Convolutional Neural Network
Ilyass Abouelaziz, Aladine Chetouani, Mohammed El Hassouni, Hocine Cherifi · 2018
3D meshes are usually affected by various visual distortions during their transmission and geometric processing. In this paper we propose a reduced reference method for mesh visual quality assessment. The method compares features extracted from the distorted mesh and the original one using a convolutional neural network in order to estimate the visual quality score. The perceptual distance between two meshes is computed as the Kullback-Leibler divergence between the two sets of feature vectors. Experimental results from two subjective databases (LIRIS masking database and LIRIS/EPFL general purpose database) and comparisons with seven objective metrics cited in the state-of-the-art demonstrate the efficacy of the proposed metric in terms of the correlation to the mean opinion scores across these databases.