Texture Synthesis
57 papers with code • 0 benchmarks • 3 datasets
The fundamental goal of example-based Texture Synthesis is to generate a texture, usually larger than the input, that faithfully captures all the visual characteristics of the exemplar, yet is neither identical to it, nor exhibits obvious unnatural looking artifacts.
Source: Non-Stationary Texture Synthesis by Adversarial Expansion
Benchmarks
These leaderboards are used to track progress in Texture Synthesis
3D-FUTURE
QST
CBTex
Most implemented papers
Texture Synthesis Using Convolutional Neural Networks
Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition.
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
chuanli11/CNNMRF
•
•
CVPR 2016
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images.
Learning Texture Manifolds with the Periodic Spatial GAN
zalandoresearch/psgan
•
•
ICML 2017
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.
Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
imransalam/style-transfer-tensorflow-2.0
•
•
These losses can improve the quality of large features, improve the separation of content and style, and offer artistic controls such as paint by numbers.
Incorporating long-range consistency in CNN-based texture generation
Gatys et al. (2015) showed that pair-wise products of features in a convolutional network are a very effective representation of image textures.
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.
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
msmsajjadi/EnhanceNet-Code
•
•
ICCV 2017
Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input.
Image Inpainting via Conditional Texture and Structure Dual Generation
xiefan-guo/ctsdg
•
•
ICCV 2021
Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors.
$μ$NCA: Texture Generation with Ultra-Compact Neural Cellular Automata
google-research/self-organising-systems
•
•
We study the problem of example-based procedural texture synthesis using highly compact models.
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.
