Synthesising Dynamic Textures using Convolutional Neural Networks
By Christina M. Funke, Leon A. Gatys, Alexander S. Ecker, Matthias Bethge. 2017
18 citations recorded by the source corpus.
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.
Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Graphics and Computer-Aided Design
- Ying Nian Wu
- Jianwen Xie
- Song-Chun Zhu
- Robert Geirhos
- Konstantinos G. Derpanis
- Marcus A. Brubaker
- Matthew Tesfaldet
- Felix Wichmann
In Computer Vision and Pattern Recognition
- Song-Chun Zhu
- Ying Nian Wu
- Luc Van Gool
- Trevor Darrell
- Ming-Hsuan Yang
- Andrea Vedaldi
- Bernt Schiele
- Jianwen Xie
Citations in the corpus
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2018, background): “, 2018) as well as static and dynamic texture synthesis (Gatys et al., 2015; Funke et al., 2017) all produce excellent results using standard CNNs, while CNNbased shape transfer seems to be very difficult (Gokaslan et al.”
- Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns (2019, methodology): “[44] adopted a pre-trained ConvNet for object recognition, while Tesfaldet et al.”
- Two-Stream Convolutional Networks for Dynamic Texture Synthesis (2017, methodology): “A recent preprint [12] described preliminary results extending the framework of Gatys et al.”