HugoTini / DeepBump

Normal & height maps generation from single pictures
https://hugotini.github.io/deepbump
GNU General Public License v3.0
1.02k stars 36 forks source link
blender blender-addon generator heightmap machine-learning ml normalmap

DeepBump

DeepBump

DeepBump is a machine-learning driven tool to generate normal & height maps from single pictures. See this blog post for an introduction.

Installation

1) Download DeepBump as a ZIP.

2) In Blender, go to Edit -> Preferences -> Add-ons -> Install and select the downloaded ZIP file. Then enable the add-on.

3) In the add-on preference, click the 'Install dependencies' button (this requires an internet connection and might take a while). In case of error, try running Blender as administrator for this step.

By installing those dependencies, be aware of Microsoft conditions. This add-on use available APIs to disable telemetry.

Usage

Check the blog post first video.

In the Shader Editor, in the right panel under the DeepBump tab:

Color (albedo) → Normals : Select a color image node and click Generate Normal Map.

Normals → Height (displacement) : Select the generated normal map image node and click Generate Height Map.

Normals → Curvature : Select the generated normal map image node and click Generate Curvature Map.

For command-line usage, see cli.md.

License

This repo is under the GPL license. The training code is currently not available.