Synthesising Dynamic Textures using Convolutional Neural Networks

02/22/2017

∙

by   Christina M. Funke, et al.

∙

0

∙

share

Here we present a parametric model for dynamic textures. The model is based on spatiotemporal summary statistics computed from the feature representations of a Convolutional Neural Network (CNN) trained on object recognition. We demonstrate how the model can be used to synthesise new samples of dynamic textures and to predict motion in simple movies.