From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators

2016/03/07 by Paul Upchurch, Noah Snavely, Upchurch, Paul +3 · 3 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Speech Recognition and Synthesis #Topic Modeling #cs.CV

paper · pdf · doi:10.48550/arxiv.1603.02003

arxiv created 2016/03/07 · openalex publication_date 2016/03/07 · arxiv updated 2016/03/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Theano: new features and speed improvements
• Deep Convolutional Inverse Graphics Network
• Unsupervised Domain Adaptation by Backpropagation
• VISALOGY: Answering Visual Analogy Questions
• Gradient-based learning applied to document recognition

Cited by

• Generative Adversarial Networks with Inverse Transformation Unit
• A Unified Framework for Generalizable Style Transfer: Style and Content Separation
• Learning Perceptual Manifold of Fonts

Related

• Exploring the Neural Algorithm of Artistic Style
• Style Transfer: From Stitching to Neural Networks
• StyleBank: An Explicit Representation for Neural Image Style Transfer
• Neural Style Transfer: A Review
• Neural arbitrary style transfer for portrait images using the attention mechanism