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

arXiv: https://arxiv.org/abs/1603.02003 · HTML: https://mlsanity.com/paper/1603.02003/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2016.

## Built on by (most cited first, 14 of 14)

- [Visual Prompting via Image Inpainting](https://mlsanity.com/paper/2209.00647/) (2022)
- [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021)
- [Customizing Text-to-Image Models with a Single Image Pair](https://mlsanity.com/paper/2405.01536/) (2024)
- [ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity](https://mlsanity.com/paper/2103.09776/) (2021)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields](https://mlsanity.com/paper/2307.16897/) (2023)
- [GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation](https://mlsanity.com/paper/2207.09649/) (2022)
- [DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2212.14742/) (2022)
- [Font Completion and Manipulation by Cycling Between Multi-Modality Representations](https://mlsanity.com/paper/2108.12965/) (2021)
- [Neural Font Rendering](https://mlsanity.com/paper/2211.14802/) (2022)
- [Neural 3D Video Synthesis from Multi-view Video](https://mlsanity.com/paper/2103.02597/) (2021)
- [Learning Perceptual Manifold of Fonts](https://mlsanity.com/paper/2106.09198/) (2021)
- [Natural Scene Text Editing Based on AI](https://mlsanity.com/paper/2111.15475/) (2021)
- [Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training](https://mlsanity.com/paper/2609.13239/) (2026)

## Abstract (arXiv)

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.