Texture Synthesis
State-of-the-art leaderboards
Greatest papers with code
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
CVPR 2016
• awentzonline/image-analogies
• 
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images. The generative MRF acts on higher-levels of a dCNN feature pyramid, controling the image layout at an abstract level.
Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis
CVPR 2017 • DmitryUlyanov/texture_nets
The recent work of Gatys et al., who characterized the style of an image by the statistics of convolutional neural network filters, ignited a renewed interest in the texture generation and image stylization problems. While their image generation technique uses a slow optimization process, recently several authors have proposed to learn generator neural networks that can produce similar outputs in one quick forward pass.
Texture Synthesis Using Convolutional Neural Networks
NeurIPS 2015 • DmitryUlyanov/texture_nets
Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion.
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
• chuanli11/MGANs
• 
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).
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
CVPR 2018
• ryersonvisionlab/two-stream-dyntex-synth
•
We introduce a two-stream model for dynamic texture synthesis. Given an input dynamic texture, statistics of filter responses from the object recognition ConvNet encapsulate the per-frame appearance of the input texture, while statistics of filter responses from the optical flow ConvNet model its dynamics.
OBJECT RECOGNITION OPTICAL FLOW ESTIMATION STYLE TRANSFER TEXTURE SYNTHESIS
Texture Synthesis with Spatial Generative Adversarial Networks
Generative adversarial networks (GANs) are a recent approach to train generative models of data, which have been shown to work particularly well on image data. In the current paper we introduce a new model for texture synthesis based on GAN learning.
Learning Texture Manifolds with the Periodic Spatial GAN
ICML 2017
• zalandoresearch/psgan
• 
First, we can learn multiple textures from datasets of one or more complex large images. Second, we show that the image generation with PSGANs has properties of a texture manifold: we can smoothly interpolate between samples in the structured noise space and generate novel samples, which lie perceptually between the textures of the original dataset.
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
ICCV 2017
• msmsajjadi/EnhanceNet-Code
•
Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the human perception of image quality.
#13 best model for
Image Super-Resolution on Set14 - 4x upscaling
TextureGAN: Controlling Deep Image Synthesis with Texture Patches
CVPR 2018
• janesjanes/Pytorch-TextureGAN
•
In this paper, we investigate deep image synthesis guided by sketch, color, and texture. Previous image synthesis methods can be controlled by sketch and color strokes but we are the first to examine texture control.
Incorporating long-range consistency in CNN-based texture generation
• anujdutt9/Artistic-Style-Transfer-using-Keras-Tensorflow
Gatys et al. (2015) showed that pair-wise products of features in a convolutional network are a very effective representation of image textures. We propose a simple modification to that representation which makes it possible to incorporate long-range structure into image generation, and to render images that satisfy various symmetry constraints.