MohamedAfham/CrossPoint
Official implementation of "CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding" (CVPR, 2022)
This project helps computer vision researchers and engineers improve how computers understand 3D shapes. It takes raw 3D point cloud data and corresponding 2D images, and outputs trained models that can recognize objects or parts of objects more effectively. It is designed for those working on tasks like 3D object classification or segmentation.
263 stars. No commits in the last 6 months.
Use this if you are a computer vision researcher or practitioner looking to train robust 3D object recognition models using both 3D point clouds and 2D image data.
Not ideal if you primarily work with only 2D images or already have sufficiently labeled 3D datasets for your specific object recognition task.
Stars
263
Forks
29
Language
Python
License
—
Category
Last pushed
Apr 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/MohamedAfham/CrossPoint"
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