arXiv Analytics

Sign in

arXiv:1702.07006 [cs.CV]AbstractReferencesReviewsResources

Synthesising Dynamic Textures using Convolutional Neural Networks

Christina M. Funke, Leon A. Gatys, Alexander S. Ecker, Matthias Bethge

Published 2017-02-22Version 1

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.

Related articles: Most relevant | Search more
arXiv:1511.05960 [cs.CV] (Published 2015-11-18)
ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
arXiv:1609.02132 [cs.CV] (Published 2016-09-07)
UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory
arXiv:1609.08965 [cs.CV] (Published 2016-09-28)
Graph Based Convolutional Neural Network