ReshotAI/gaussian-painters

Gaussian Painters using 3D Gaussian Splatting

38
/ 100
Emerging

Extends 3D Gaussian Splatting to synthesize 2D images through a single-camera COLMAP setup with sparse point initialization, enabling creative effects like steganography and lenticular imaging. The approach samples 100 keypoints from input images as the initial point cloud, then leverages standard Gaussian Splatting optimization to reconstruct the image while supporting view-dependent effects via spherical harmonics. Includes dataset generation scripts (`create_dataset.py`, `create_dataset2.py`, etc.) that prepare synthetic training data and integrate with the SIBR visualizer for real-time optimization monitoring.

399 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

399

Forks

21

Language

Python

License

Last pushed

Aug 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ReshotAI/gaussian-painters"

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