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.
@article{arxiv.1702.07006,
title = {Synthesising Dynamic Textures using Convolutional Neural Networks},
author = {Christina M. Funke and Leon A. Gatys and Alexander S. Ecker and Matthias Bethge},
journal= {arXiv preprint arXiv:1702.07006},
year = {2017}
}