Texture Synthesis
40 papers with code • 0 benchmarks • 2 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
Hypersim
3D-FUTURE
Greatest papers with code
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
awentzonline/image-analogies
•
•
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.
Texture Memory-Augmented Deep Patch-Based Image Inpainting
By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions.
Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis
DmitryUlyanov/texture_nets
•
•
CVPR 2017
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.
Texture Synthesis Using Convolutional Neural Networks
DmitryUlyanov/texture_nets
•
•
NeurIPS 2015
Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition.
Learning Texture Transformer Network for Image Super-Resolution
In this paper, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys in a transformer, respectively.
Non-Stationary Texture Synthesis by Adversarial Expansion
jessemelpolio/non-stationary_texture_syn
•
•
We demonstrate that this conceptually simple approach is highly effective for capturing large-scale structures, as well as other non-stationary attributes of the input exemplar.
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.
StructureFlow: Image Inpainting via Structure-aware Appearance Flow
RenYurui/StructureFlow
•
•
ICCV 2019
Image inpainting techniques have shown significant improvements by using deep neural networks recently.
Two-Stream Convolutional Networks for Dynamic Texture Synthesis
ryersonvisionlab/two-stream-dyntex-synth
•
•
CVPR 2018
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.
TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures
We tackle the problem of texture synthesis in the setting where many input images are given and a large-scale output is required.