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 91100 of 280 papers

TitleStatusHype
Semantics-Aligned Representation Learning for Person Re-identificationCode0
Finding Biological Plausibility for Adversarially Robust Features via Metameric TasksCode0
Fast Texture Synthesis via Pseudo OptimizerCode0
LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion ModelsCode0
Deep Audio PriorCode0
Learning Texture Manifolds with the Periodic Spatial GANCode0
Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein LossCode0
μNCA: Texture Generation with Ultra-Compact Neural Cellular AutomataCode0
Co-occurrence Based Texture SynthesisCode0
High resolution neural texture synthesis with long range constraintsCode0
Show:102550
← PrevPage 10 of 28Next →

No leaderboard results yet.