Yochengliu/Relation-Shape-CNN
Relation-Shape Convolutional Neural Network for Point Cloud Analysis (CVPR 2019 Oral & Best paper finalist)
This project helps classify 3D object shapes and segment their parts using point cloud data. You input raw 3D point clouds of objects, and it outputs labels identifying the object's category (e.g., 'chair', 'car') or segmenting its individual components (e.g., 'chair leg', 'chair back'). This is ideal for researchers or engineers working in 3D computer vision, robotics, or augmented reality who need precise 3D object understanding.
426 stars. No commits in the last 6 months.
Use this if you need a robust method to automatically identify 3D objects or precisely delineate their parts from raw point cloud scans for tasks like scene understanding or robotic manipulation.
Not ideal if your primary input data is 2D images or video, as this system is specifically designed for 3D point cloud analysis.
Stars
426
Forks
73
Language
Python
License
MIT
Category
Last pushed
Sep 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Yochengliu/Relation-Shape-CNN"
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