# BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioning

arXiv: https://arxiv.org/abs/2212.01589 · HTML: https://mlsanity.com/paper/2212.01589/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 3 Dec 2022.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Improved Techniques for Training Single-Image GANs](https://mlsanity.com/paper/2003.11512/) (2020)
- [Non-Stationary Texture Synthesis by Adversarial Expansion](https://mlsanity.com/paper/1805.04487/) (2018)
- [Learning Texture Manifolds with the Periodic Spatial GAN](https://mlsanity.com/paper/1705.06566/) (2017)
- [Deep Geometric Texture Synthesis](https://mlsanity.com/paper/2007.00074/) (2020)
- [Texture Synthesis with Spatial Generative Adversarial Networks](https://mlsanity.com/paper/1611.08207/) (2016)
- [Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample](https://mlsanity.com/paper/2006.12226/) (2020)
- [TOAD-GAN: Coherent Style Level Generation from a Single Example](https://mlsanity.com/paper/2008.01531/) (2020)
- [Few-shot Image Generation with Mixup-based Distance Learning](https://mlsanity.com/paper/2111.11672/) (2021)
- [Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture](https://mlsanity.com/paper/1901.03447/) (2019)
- [Catch-A-Waveform: Learning to Generate Audio from a Single Short Example](https://mlsanity.com/paper/2106.06426/) (2021)
- [Barycenters of Natural Images -- Constrained Wasserstein Barycenters for Image Morphing](https://mlsanity.com/paper/1912.11545/) (2019)
- [Learning Diagnosis of COVID-19 from a Single Radiological Image](https://mlsanity.com/paper/2006.12220/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [Controllable Single-shot Animation Blending with Temporal Conditioning](https://mlsanity.com/paper/2508.18525/) (2025)

## Abstract (arXiv)

Training a generative model on a single image has drawn significant attention in recent years. Single image generative methods are designed to learn the internal patch distribution of a single natural image at multiple scales. These models can be used for drawing diverse samples that semantically resemble the training image, as well as for solving many image editing and restoration tasks that involve that particular image. Here, we introduce an extended framework, which allows to simultaneously learn the internal distributions of several images, by using a single model with spatially varying image-identity conditioning. Our BlendGAN opens the door to applications that are not supported by single-image models, including morphing, melding, and structure-texture fusion between two or more arbitrary images.