# Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1604.04382 · HTML: https://mlsanity.com/paper/1604.04382/

## Key facts

- Cited by 192 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2016.

## Built on by (most cited first, 30 of 192)

- [PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers](https://mlsanity.com/paper/2111.12710/) (2021)
- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization](https://mlsanity.com/paper/2103.06818/) (2021)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [Enhancing Photorealism Enhancement](https://mlsanity.com/paper/2105.04619/) (2021)
- [Region-aware Adaptive Instance Normalization for Image Harmonization](https://mlsanity.com/paper/2106.02853/) (2021)
- [Image Inpainting via Conditional Texture and Structure Dual Generation](https://mlsanity.com/paper/2108.09760/) (2021)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection](https://mlsanity.com/paper/2104.14535/) (2021)
- [Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer](https://mlsanity.com/paper/2104.05376/) (2021)
- [Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition](https://mlsanity.com/paper/2103.16019/) (2021)
- [HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance](https://mlsanity.com/paper/2307.07829/) (2023)
- [DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Models](https://mlsanity.com/paper/2302.06826/) (2023)
- [General Image-to-Image Translation with One-Shot Image Guidance](https://mlsanity.com/paper/2307.14352/) (2023)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers](https://mlsanity.com/paper/2104.06757/) (2021)
- [IMAGINE: Image Synthesis by Image-Guided Model Inversion](https://mlsanity.com/paper/2104.05895/) (2021)
- [A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU](https://mlsanity.com/paper/2305.17473/) (2023)
- [RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs using a Novel Multi-scale Generative Adversarial Network](https://mlsanity.com/paper/2101.00535/) (2021)
- [Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis](https://mlsanity.com/paper/2104.05703/) (2021)
- [GANimator: Neural Motion Synthesis from a Single Sequence](https://mlsanity.com/paper/2205.02625/) (2022)
- [AesUST: Towards Aesthetic-Enhanced Universal Style Transfer](https://mlsanity.com/paper/2208.13016/) (2022)
- [Diffusion-based Document Layout Generation](https://mlsanity.com/paper/2303.10787/) (2023)
- [A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging](https://mlsanity.com/paper/2106.15944/) (2021)
- [MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames](https://mlsanity.com/paper/2102.12841/) (2021)
- [Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devices](https://mlsanity.com/paper/2106.15202/) (2021)
- [Style-ERD: Responsive and Coherent Online Motion Style Transfer](https://mlsanity.com/paper/2203.02574/) (2022)
- [Z^*: Zero-shot Style Transfer via Attention Rearrangement](https://mlsanity.com/paper/2311.16491/) (2023)

## Abstract (arXiv)

This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative neural networks for efficient texture synthesis. While deep neural network approaches have recently demonstrated remarkable results in terms of synthesis quality, they still come at considerable computational costs (minutes of run-time for low-res images). Our paper addresses this efficiency issue. Instead of a numerical deconvolution in previous work, we precompute a feed-forward, strided convolutional network that captures the feature statistics of Markovian patches and is able to directly generate outputs of arbitrary dimensions. Such network can directly decode brown noise to realistic texture, or photos to artistic paintings. With adversarial training, we obtain quality comparable to recent neural texture synthesis methods. As no optimization is required any longer at generation time, our run-time performance (0.25M pixel images at 25Hz) surpasses previous neural texture synthesizers by a significant margin (at least 500 times faster). We apply this idea to texture synthesis, style transfer, and video stylization.