JADGardner/RENI

Code for the paper "Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior" https://arxiv.org/abs/2206.03858 Accepted to NeurIPS 2022!

31
/ 100
Emerging

This project helps computer graphics artists and researchers synthesize realistic natural lighting for virtual scenes and objects. By inputting sparse or incomplete environment map data, it generates a full, high-quality representation of natural illumination. This is ideal for 3D artists, VFX professionals, and researchers working on rendering and computer vision tasks who need to realistically light virtual environments.

No commits in the last 6 months.

Use this if you need to generate plausible and consistent natural illumination for virtual scenes, even when starting with limited or partial lighting information.

Not ideal if you require highly specific, non-naturalistic, or completely custom lighting setups, or if computational efficiency for real-time applications is your primary concern.

3D-rendering computer-graphics virtual-photography VFX environment-lighting
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

45

Forks

3

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Nov 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JADGardner/RENI"

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