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

Showing 6170 of 280 papers

TitleStatusHype
Text-Guided Texturing by Synchronized Multi-View DiffusionCode1
Conditional Generative ConvNets for Exemplar-based Texture SynthesisCode0
A Structure-Guided Diffusion Model for Large-Hole Image CompletionCode0
Semantics-Aligned Representation Learning for Person Re-identificationCode0
Non-Stationary Texture Synthesis by Adversarial ExpansionCode0
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial NetworksCode0
Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein LossCode0
A note on the evaluation of generative modelsCode0
LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion ModelsCode0
Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configurationCode0
Show:102550
← PrevPage 7 of 28Next →

No leaderboard results yet.