cszyzhang/riconv2
The official source codes for the riconv++ (IJCV2022) paper
This project helps computer vision researchers and AI practitioners accurately classify and segment 3D objects represented as point clouds, regardless of their orientation. You provide 3D scan data or digital models (point clouds), and it outputs labels for entire objects or individual parts, even if the object is rotated. This is useful for anyone working with 3D data recognition, like those in robotics, autonomous vehicles, or 3D modeling.
No commits in the last 6 months.
Use this if you need to reliably identify or categorize 3D objects from point cloud data, where the objects might appear in various rotations, without having to re-train your recognition system for every angle.
Not ideal if your primary task involves processing 2D images, or if you need to perform tasks like 3D reconstruction rather than classification or segmentation.
Stars
31
Forks
6
Language
Python
License
MIT
Category
Last pushed
Nov 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cszyzhang/riconv2"
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