SOTAVerified

Texture Synthesis

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 261–270 of 280 papers

TitleStatusHype
Style-Transfer via Texture-SynthesisCode0
Incorporating long-range consistency in CNN-based texture generationCode1
Texture Synthesis Using Shallow Convolutional Networks with Random Filters—0
Patch-based Texture Synthesis for Image Inpainting—0
Texture Synthesis Through Convolutional Neural Networks and Spectrum ConstraintsCode0
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial NetworksCode0
Combining Markov Random Fields and Convolutional Neural Networks for Image SynthesisCode1
A note on the evaluation of generative modelsCode0
Texture Modelling with Nested High-order Markov-Gibbs Random Fields—0
Generative Image Modeling Using Spatial LSTMs—0
Show:102550
← PrevPage 27 of 28Next →

No leaderboard results yet.