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 251–260 of 280 papers

TitleStatusHype
A Procedural Texture Generation Framework Based on Semantic Descriptions—0
Perception Driven Texture Generation—0
Diversified Texture Synthesis with Feed-forward Networks—0
Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram LossesCode0
Super-resolution Using Constrained Deep Texture Synthesis—0
Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis—0
EnhanceNet: Single Image Super-Resolution Through Automated Texture SynthesisCode0
On Random Weights for Texture Generation in One Layer Neural Networks—0
Awesome Typography: Statistics-Based Text Effects TransferCode0
Texture Synthesis with Spatial Generative Adversarial NetworksCode0
Show:102550
← PrevPage 26 of 28Next →

No leaderboard results yet.