Arbitrary style transfer with attentional networks via unbalanced optimal transport

Fast Patch-based Style Transfer of Arbitrary Style

Artistic style transfer is an image synthesis problem where the content of an image is reproduced with the style of another. Recent works show that a visually appealing style transfer can be achieved by using the hidden activations of a pretrained convolutional neural network. However, existing methods either apply (i) an optimization procedure that works for any style image but is very expensi...

Eulerian models and algorithms for unbalanced optimal transport

Universal Style Transfer via Feature Transforms

Universal style transfer aims to transfer any arbitrary visual styles to content images. Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. In this paper, we present a simple yet effective method that tackles these limitations without training on any pre-defined styles. The...

Towards Metamerism via Foveated Style Transfer

Given the recent successes of deep learning applied to style transfer and texture synthesis, we propose a new theoretical framework to construct visual metamers: a family of perceptually identical, yet physically different images. We review work both in neuroscience related to metameric stimuli, as well as computer vision research in style transfer. We propose our NeuroFovea metamer model that ...

Optimal Placement and Sizing of Distributed Generations in Unbalanced Distribution Networks Considering Load Models and Uncertainties

Development of distributed generations’ technology, trends in the use of these sources to improve some of the problems such as high losses, low reliability, low power quality and high costs in distributed networks. Choose the correct location to install and proper capacity of these sources, such as important things that must be considered in their use. Since distribution networks are actu...