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 231–240 of 280 papers

TitleStatusHype
Generator Pyramid for High-Resolution Image Inpainting—0
GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation—0
Geometry-Aware Texture Generation for 3D Head Modeling with Artist-driven Control—0
Geometry Guided Adversarial Facial Expression Synthesis—0
GramGAN: Deep 3D Texture Synthesis From 2D Exemplars—0
Graphcut Texture Synthesis for Single-Image Superresolution—0
Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes—0
HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation—0
ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling—0
Image Inpainting for High-Resolution Textures using CNN Texture Synthesis—0
Show:102550
← PrevPage 24 of 28Next →

No leaderboard results yet.