Lilac-Lee/PointNetLK_Revisited
Implementation for our CVPR 2021 oral paper "PointNetLK Revisited".
This project helps computer vision researchers align two 3D point clouds that represent the same object or scene from slightly different perspectives. You provide two point clouds, and it outputs the precise geometric transformation needed to make them overlap. It's ideal for academics and practitioners working with 3D data.
No commits in the last 6 months.
Use this if you need to accurately align two partially overlapping 3D point cloud scans of an object or environment.
Not ideal if your point clouds have very little overlap or require a global alignment from vastly different viewpoints.
Stars
52
Forks
5
Language
Python
License
MIT
Category
Last pushed
Apr 13, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Lilac-Lee/PointNetLK_Revisited"
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