jiachens/ModelNet40-C

Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296

40
/ 100
Emerging

This project offers a specialized dataset and pre-trained models for evaluating how well 3D object recognition systems can identify common shapes even when the scan data is corrupted or imperfect. It takes 3D point cloud data of objects as input and classifies them, providing a measure of how robustly a given recognition model performs under various real-world data imperfections. It is designed for researchers and engineers working on computer vision, robotics, or autonomous systems who need to develop and test reliable 3D object recognition.

216 stars. No commits in the last 6 months.

Use this if you are developing or evaluating 3D object recognition models and need to rigorously test their performance when faced with real-world sensor noise, occlusions, or other data corruptions.

Not ideal if you are looking for a general-purpose 3D object recognition solution for clean, ideal data, or if your primary focus is not on corruption robustness.

3D-object-recognition robotics-perception autonomous-systems computer-vision point-cloud-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

216

Forks

21

Language

Python

License

BSD-3-Clause

Last pushed

Aug 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jiachens/ModelNet40-C"

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