Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Incorporating long-range consistency in CNN-based texture generation
Guillaume Berger, Roland Memisevic
Nov 04, 2016 (modified: Feb 09, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:Gatys et al. (2015) showed that pair-wise products of features in a convolutional network are a very effective representation of image textures. We propose a simple modification to that representation which makes it possible to incorporate long-range structure into image generation, and to render images that satisfy various symmetry constraints. We show how this can greatly improve rendering of regular textures and of images that contain other kinds of symmetric structure. We also present applications to inpainting and season transfer.
TL;DR:We propose a simple extension to the Gatys et al. algorithm which makes it possible to incorporate long-range structure into texture generation.
Keywords:Computer vision, Deep learning
Enter your feedback below and we'll get back to you as soon as possible.