Karbo123/RGBD-Diffusion

RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models

31
/ 100
Emerging

This project helps create detailed, new virtual environments or scenes. You provide existing 3D scans (like those from a 3D scanner that capture both color and depth), and it generates new, continuous views as if a camera were moving through the scene. This is useful for researchers and developers working on virtual reality, robotics, or synthetic data generation for computer vision.

No commits in the last 6 months.

Use this if you need to generate realistic, novel 3D scenes or extend existing 3D scans with new camera perspectives and detailed depth information.

Not ideal if you are looking for a simple drag-and-drop tool for non-technical users, or if you don't have existing 3D scan data to work with.

3D-scene-generation virtual-environment-creation robotics-simulation synthetic-data-generation computer-vision-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

99

Forks

3

Language

Python

License

MIT

Last pushed

Mar 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Karbo123/RGBD-Diffusion"

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