Traverse-Research/NeuBTF

Neural Bidirectional Texture Function Compression and Rendering

21
/ 100
Experimental

This project helps 3D artists, game developers, or product designers create highly realistic digital representations of materials. It takes detailed measurements of how a physical material reflects light from different angles and compresses this data into a format that can then be rendered efficiently in 3D software like Mitsuba 2. The output is a visually accurate, compressed digital material that behaves just like its real-world counterpart under various lighting conditions.

No commits in the last 6 months.

Use this if you need to create highly realistic 3D models of objects with complex surface appearances, ensuring their digital representation accurately reflects how light interacts with the actual physical material.

Not ideal if you are looking for a simple texture mapping solution or a tool for general-purpose 3D modeling without specific material accuracy requirements.

3D-rendering material-scanning product-visualization computer-graphics virtual-prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 06, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Traverse-Research/NeuBTF"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.