Texture Interpolation for Probing Visual Perception.

ABSTRACT: Texture synthesis models are important tools for understanding visual processing. In particular, statistical approaches based on neurally relevant features have been instrumental in understanding aspects of visual perception and of neural coding. New deep learning-based approaches further improve the quality of synthetic textures. Yet, it is still unclear why deep texture synthesis performs so well, and applications of this new framework to probe visual perception are scarce. Here, we show that distributions of deep convolutional neural network (CNN) activations of a texture are well described by elliptical distributions and therefore, following optimal transport theory, constraining their mean and covariance is sufficient to generate new texture samples. Then, we propose the natural geode

SUBMITTER: Vacher J 

PROVIDER: S-EPMC9681139 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature