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.
This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images.
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.
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.
Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition.
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.
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.
This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative neural networks for efficient texture synthesis.
Image inpainting techniques have shown significant improvements by using deep neural networks recently.
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.