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 226250 of 280 papers

TitleStatusHype
User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks0
Re-Identification Supervised Texture Generation0
Texture Synthesis Guided Deep Hashing for Texture Image Retrieval0
FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchronized GANsCode0
Context-Aware Text-Based Binary Image Stylization and Synthesis0
Second-order Democratic Aggregation0
Texture Mixing by Interpolating Deep Statistics via Gaussian Models0
Non-Stationary Texture Synthesis by Adversarial ExpansionCode0
Learning the Synthesizability of Dynamic Texture Samples0
Multiscale Sparse Microcanonical Models0
Improved Style Transfer by Respecting Inter-layer Correlations0
“Style” Transfer for Musical Audio Using Multiple Time-Frequency Representations0
Texture Synthesis with Recurrent Variational Auto-EncoderCode0
On Using Backpropagation for Speech Texture Generation and Voice Conversion0
Geometry Guided Adversarial Facial Expression Synthesis0
Image Inpainting for High-Resolution Textures using CNN Texture Synthesis0
GANosaic: Mosaic Creation with Generative Texture Manifolds0
Fashioning with Networks: Neural Style Transfer to Design Clothes0
A survey of exemplar-based texture synthesis0
Synthesis of Near-regular Natural Textures0
Two-Stream Convolutional Networks for Dynamic Texture SynthesisCode0
Graphcut Texture Synthesis for Single-Image Superresolution0
TextureGAN: Controlling Deep Image Synthesis with Texture PatchesCode0
Towards Metamerism via Foveated Style TransferCode0
Learning Texture Manifolds with the Periodic Spatial GANCode0
Show:102550
← PrevPage 10 of 12Next →

No leaderboard results yet.