Chen-Suyi/SIRA_Pytorch

[ICCV 2023] SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration, Pytorch implementation

33
/ 100
Emerging

This project helps robotics engineers and 3D vision researchers accurately align multiple 3D point cloud scans of a scene. It takes noisy 3D point cloud data from real-world sensors and processes it to be more consistent with synthetic training data. The output is a registered 3D point cloud, allowing for more reliable scene reconstruction and object recognition, especially for indoor and outdoor environments.

Use this if you need to precisely align 3D point cloud data from different scans, especially when your models are trained on synthetic data and struggle with real-world sensor noise.

Not ideal if you are working with 2D image data or if your primary need is not 3D scene reconstruction or object pose estimation.

3D-scanning robot-localization augmented-reality computer-vision scene-reconstruction
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

25

Forks

Language

Python

License

Apache-2.0

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Chen-Suyi/SIRA_Pytorch"

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