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 141–150 of 280 papers

TitleStatusHype
Emotion-Controllable Generalized Talking Face Generation—0
AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis—0
Exemplar-based Pattern Synthesis with Implicit Periodic Field Network—0
3D microstructural generation from 2D images of cement paste using generative adversarial networksCode0
Marginal Contrastive Correspondence for Guided Image Generation—0
Generalized Rectifier Wavelet Covariance Models For Texture SynthesisCode0
Texture Generation Using Dual-Domain Feature Flow with Multi-View Hallucinations—0
Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2Code1
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution PriorsCode2
Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis—0
Show:102550
← PrevPage 15 of 28Next →

No leaderboard results yet.