shinke-li/pointcvar
The official implementation code of Paper "PointCVaR: Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification" in AAAI 2024 (Oral)
This helps improve the reliability of systems that classify 3D objects using point clouds. It takes raw 3D point cloud data, potentially with various types of noise or errors, and outputs a cleaner, more robust classification of the objects within those point clouds. This is for researchers, engineers, or scientists working with 3D scanning, robotics, or autonomous systems who need accurate object identification.
No commits in the last 6 months.
Use this if you are working with 3D point cloud classification models and need to ensure they are robust against different kinds of noise and outliers, leading to more reliable object recognition.
Not ideal if you are looking for a general-purpose 3D point cloud processing tool that doesn't specifically focus on classification robustness or outlier removal.
Stars
16
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/shinke-li/pointcvar"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
drprojects/superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds