# Structural-analogy from a Single Image Pair

arXiv: https://arxiv.org/abs/2004.02222 · HTML: https://mlsanity.com/paper/2004.02222/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2020.

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

- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023)
- [Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2402.03286/) (2024)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps](https://mlsanity.com/paper/2201.05120/) (2022)
- [Diverse Generation from a Single Video Made Possible](https://mlsanity.com/paper/2109.08591/) (2021)
- [ExSinGAN: Learning an Explainable Generative Model from a Single Image](https://mlsanity.com/paper/2105.07350/) (2021)
- [CharacterGAN: Few-Shot Keypoint Character Animation and Reposing](https://mlsanity.com/paper/2102.03141/) (2021)
- [Generating Non-Stationary Textures using Self-Rectification](https://mlsanity.com/paper/2401.02847/) (2024)
- [TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets](https://mlsanity.com/paper/2105.06219/) (2021)
- [Neural Photometry-guided Visual Attribute Transfer](https://mlsanity.com/paper/2112.02520/) (2021)
- [Disentangling Structure and Appearance in ViT Feature Space](https://mlsanity.com/paper/2311.12193/) (2023)
- [Efficient and Training-Free Single-Image Diffusion Models](https://mlsanity.com/paper/2606.04299/) (2026)
- [Diverse Video Generation from a Single Video](https://mlsanity.com/paper/2205.05725/) (2022)

## Abstract (arXiv)

The task of unsupervised image-to-image translation has seen substantial advancements in recent years through the use of deep neural networks. Typically, the proposed solutions learn the characterizing distribution of two large, unpaired collections of images, and are able to alter the appearance of a given image, while keeping its geometry intact. In this paper, we explore the capabilities of neural networks to understand image structure given only a single pair of images, A and B. We seek to generate images that are structurally aligned: that is, to generate an image that keeps the appearance and style of B, but has a structural arrangement that corresponds to A. The key idea is to map between image patches at different scales. This enables controlling the granularity at which analogies are produced, which determines the conceptual distinction between style and content. In addition to structural alignment, our method can be used to generate high quality imagery in other conditional generation tasks utilizing images A and B only: guided image synthesis, style and texture transfer, text translation as well as video translation. Our code and additional results are available in https://github.com/rmokady/structural-analogy/.