engelnico/point-transformer
This is the official repository of the original Point Transformer architecture.
This project offers a deep learning architecture specifically designed to understand and process 3D point cloud data. It takes raw, unstructured sets of 3D points, such as those representing real-world objects, and transforms them into organized feature lists. This allows for tasks like identifying entire objects or segmenting an object into its component parts, making it useful for researchers and engineers working with 3D scanning or computer vision.
No commits in the last 6 months.
Use this if you need to classify 3D point clouds (e.g., recognizing different types of furniture from scan data) or perform part segmentation on 3D objects (e.g., separating a car model into its wheels, doors, and chassis).
Not ideal if your data is not in a 3D point cloud format or if you require real-time processing with very low latency on embedded systems.
Stars
42
Forks
8
Language
Python
License
—
Category
Last pushed
Apr 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/engelnico/point-transformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrick-llgc/Learning-Deep-Learning
Paper reading notes on Deep Learning and Machine Learning
eric-yyjau/pytorch-superpoint
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
magicleap/SuperGluePretrainedNetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
changhao-chen/deep-learning-localization-mapping
A collection of deep learning based localization models
lucasb-eyer/pydensecrf
Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.