Perceptual misalignment of texture representations in convolutional neural networks

ArXi:2604.01341v1 Announce Type: new Mathematical modeling of visual textures traces back to Julesz's intuition that texture perception in humans is based on local correlations between image features. An influential approach for texture analysis and generation generalizes this notion to linear correlations between the nonlinear features computed by convolutional neural networks (CNNs), compiled into Gram matrices.