English

Synthesising Dynamic Textures using Convolutional Neural Networks

Computer Vision and Pattern Recognition 2017-02-24 v1

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-22T18:25:51.812Z