# Generating natural images with direct Patch Distributions Matching

arXiv: https://arxiv.org/abs/2203.11862 · HTML: https://mlsanity.com/paper/2203.11862/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 22 Mar 2022.

## Builds on (most cited first, 16 of 16)

- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning](https://mlsanity.com/paper/1705.07761/) (2017)
- [Style Transfer by Relaxed Optimal Transport and Self-Similarity](https://mlsanity.com/paper/1904.12785/) (2019)
- [Demystifying Neural Style Transfer](https://mlsanity.com/paper/1701.01036/) (2017)
- [The Contextual Loss for Image Transformation with Non-Aligned Data](https://mlsanity.com/paper/1803.02077/) (2018)
- [Generative Modeling using the Sliced Wasserstein Distance](https://mlsanity.com/paper/1803.11188/) (2018)
- [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis](https://mlsanity.com/paper/1601.04589/) (2016)
- [Improved Techniques for Training Single-Image GANs](https://mlsanity.com/paper/2003.11512/) (2020)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model](https://mlsanity.com/paper/1804.01947/) (2018)
- [Wasserstein Style Transfer](https://mlsanity.com/paper/1905.12828/) (2019)
- [Generating Novel Scene Compositions from Single Images and Videos](https://mlsanity.com/paper/2103.13389/) (2021)

## Built on by (most cited first, 27 of 27)

- [SinDDM: A Single Image Denoising Diffusion Model](https://mlsanity.com/paper/2211.16582/) (2022)
- [Attention Distillation: A Unified Approach to Visual Characteristics Transfer](https://mlsanity.com/paper/2502.20235/) (2025)
- [Patch-based 3D Natural Scene Generation from a Single Example](https://mlsanity.com/paper/2304.12670/) (2023)
- [Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures](https://mlsanity.com/paper/2407.10181/) (2024)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [Learning from small data sets: Patch-based regularizers in inverse problems for image reconstruction](https://mlsanity.com/paper/2312.16611/) (2023)
- [Wasserstein Distortion: Unifying Fidelity and Realism](https://mlsanity.com/paper/2310.03629/) (2023)
- [High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis](https://mlsanity.com/paper/2304.06433/) (2023)
- [A User's Guide to Sampling Strategies for Sliced Optimal Transport](https://mlsanity.com/paper/2502.02275/) (2025)
- [Misalignment-Robust Frequency Distribution Loss for Image Transformation](https://mlsanity.com/paper/2402.18192/) (2024)
- [Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectors](https://mlsanity.com/paper/2303.04238/) (2023)
- [Slicing Wasserstein Over Wasserstein Via Functional Optimal Transport](https://mlsanity.com/paper/2509.22138/) (2025)
- [ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion](https://mlsanity.com/paper/2502.02187/) (2025)
- [OAIR: Object-Aware Image Retargeting Using PSO and Aesthetic Quality Assessment](https://mlsanity.com/paper/2209.04804/) (2022)
- [Time Series Synthesis via Multi-scale Patch-based Generation of Wavelet Scalogram](https://mlsanity.com/paper/2211.02620/) (2022)
- [HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations](https://mlsanity.com/paper/2504.03026/) (2025)
- [Video Consistency Distance: Enhancing Temporal Consistency for Image-to-Video Generation via Reward-Based Fine-Tuning](https://mlsanity.com/paper/2510.19193/) (2025)
- [Object-IR: Leveraging Object Consistency and Mesh Deformation for Self-Supervised Image Retargeting](https://mlsanity.com/paper/2510.27236/) (2025)
- [Example-Based Feature Painting on Textures](https://mlsanity.com/paper/2511.01513/) (2025)
- [Efficient and Training-Free Single-Image Diffusion Models](https://mlsanity.com/paper/2606.04299/) (2026)
- [One-shot Generative Distribution Matching for Augmented RF-based UAV Identification](https://mlsanity.com/paper/2301.08403/) (2023)
- [Supervised Deep Learning for Content-Aware Image Retargeting with Fourier Convolutions](https://mlsanity.com/paper/2306.07383/) (2023)
- [ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction](https://mlsanity.com/paper/2510.01061/) (2025)
- [Quantized FCA: Efficient Zero-Shot Texture Anomaly Detection](https://mlsanity.com/paper/2510.15602/) (2025)
- [SinSEMI: A One-Shot Image Generation Model and Data-Efficient Evaluation Framework for Semiconductor Inspection Equipment](https://mlsanity.com/paper/2511.06740/) (2025)
- [FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generation](https://mlsanity.com/paper/2609.16594/) (2026)
- [AttenIR: Aligning Dense Visual Attention with Mesh Warping for Unsupervised Image Retargeting](https://mlsanity.com/paper/2610.17743/) (2026)

## Abstract (arXiv)

Many traditional computer vision algorithms generate realistic images by requiring that each patch in the generated image be similar to a patch in a training image and vice versa. Recently, this classical approach has been replaced by adversarial training with a patch discriminator. The adversarial approach avoids the computational burden of finding nearest neighbors of patches but often requires very long training times and may fail to match the distribution of patches. In this paper we leverage the recently developed Sliced Wasserstein Distance and develop an algorithm that explicitly and efficiently minimizes the distance between patch distributions in two images. Our method is conceptually simple, requires no training and can be implemented in a few lines of codes. On a number of image generation tasks we show that our results are often superior to single-image-GANs, require no training, and can generate high quality images in a few seconds. Our implementation is available at https://github.com/ariel415el/GPDM