Texture Synthesis Using Shallow Convolutional Networks with Random Filters
This challenges the necessity of complex deep networks for texture modeling, offering a simpler alternative for researchers in computer vision and graphics.
The authors tackled texture synthesis by showing that shallow convolutional networks with random filters can effectively model natural textures, sometimes matching or exceeding the perceptual quality of state-of-the-art deep CNN methods, though with less variability.
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.