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. |
Year | Venue | Field |
---|---|---|
2016 | international conference on learning representations | Computer vision,Image generation,Computer graphics (images),Computer science,Inpainting,Artificial intelligence,Rendering (computer graphics),Machine learning,Symmetric structure |
DocType | Volume | Citations |
Journal | abs/1606.01286 | 1 |
PageRank | References | Authors |
0.35 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guillaume Berger | 1 | 2 | 5.10 |
Roland Memisevic | 2 | 1116 | 65.87 |