Skip to content

suchithh/PBR-Generation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Controlled Texture Map Generation

Texture maps have widespread use in video games, architecture and 3D modeling but are difficult to generate and design.

We use ControlNet, a deep learning algorithm used for controlling image generation, and train it to generate normal and roughness texture maps, utilizing only the base color (Albedo Map) as the conditioning input. Based on our tests, the models also works well on received material photographs.

Dataset

We use MatSynth, the largest open-source PBR materials dataset, created by Guiseppe Vecchio and Valentin Deschaire.

Our augmentated datatset is available on Hugging Face.

Models

controlnet-rough

controlnet-normal

Usage

See hugging face card for each model.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published