Name
Title | ||
|---|---|---|
From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators. |
Abstract | ||
|---|---|---|
We propose a new neural network architecture for solving single-image analogies - the generation of an entire set of stylistically similar images from just a single input image. Solving this problem requires separating image style from content. Our network is a modified variational autoencoder (VAE) that supports supervised training of single-image analogies and in-network evaluation of outputs with a structured similarity objective that captures pixel covariances. On the challenging task of generating a 62-letter font from a single example letter we produce images with 22.4% lower dissimilarity to the ground truth than state-of-the-art. |
Year | Venue | Field |
|---|---|---|
2016 | arXiv: Computer Vision and Pattern Recognition | Autoencoder,Pattern recognition,Computer science,Font,Neural network architecture,Ground truth,Artificial intelligence,Supervised training,Pixel,Artificial neural network,Machine learning |
DocType | Volume | Citations |
Journal | abs/1603.02003 | 8 |
PageRank | References | Authors |
0.50 | 19 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Paul Upchurch | 1 | 19 | 1.77 |
| Noah Snavely | 2 | 4262 | 197.04 |
| Kavita Bala | 3 | 2046 | 138.75 |