qinzheng93/GeoTransformer
[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration
This project helps you accurately align 3D scans or point clouds, even when they only partially overlap. You provide two point clouds, and it determines how to best rotate and translate one to match the other, producing a precisely registered single point cloud. This is ideal for professionals in robotics, autonomous vehicles, or 3D scanning who need to combine multiple sensor readings into a unified view.
923 stars. No commits in the last 6 months.
Use this if you need to robustly and quickly align 3D point clouds from different perspectives or sensors, especially in situations with low overlap between scans.
Not ideal if your primary need is object detection or classification within a single point cloud, rather than aligning two different point clouds.
Stars
923
Forks
109
Language
Python
License
MIT
Category
Last pushed
Nov 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/qinzheng93/GeoTransformer"
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