Texture Synthesis Using Shallow Convolutional Networks with Random Filters
arXiv:1606.00021
Abstract
Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classified as being more similar then patches from different textures. Samples synthesized from the model capture spatial correlations on scales much larger then the receptive field size, and sometimes even rival or surpass the perceptual quality of state of the art texture models (but show less variability). The current state of the art in parametric texture synthesis relies on the multi-layer feature space of deep CNNs that were trained on natural images. Our finding suggests that such optimized multi-layer feature spaces are not imperative for texture modeling. Instead, much simpler shallow and convolutional networks can serve as the basis for novel texture synthesis algorithms.
9 pages, 4 figures
References in corpus (3)
Cited by in corpus (14)
- Audio style transfer
- Bilinear CNNs for Fine-grained Visual Recognition
- Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
- Visual Attribute Transfer through Deep Image Analogy
- Adversarial Reprogramming of Neural Networks
- Applying Visual Domain Style Transfer and Texture Synthesis Techniques to Audio - Insights and Challenges
- Unifying local and non-local signal processing with graph CNNs
- Sound texture synthesis using convolutional neural networks
- Mechanisms of Artistic Creativity in Deep Learning Neural Networks
- Synthesizing Diverse, High-Quality Audio Textures
- How big can style be? Addressing high dimensionality for recommending with style
- On Random Weights for Texture Generation in One Layer Neural Networks
- Environment Transfer for Distributed Systems
- Macrocanonical Models for Texture Synthesis