charlesq34/frustum-pointnets
PointNet-based deep learning system for 3D object detection from RGB-D point clouds.
Not currently ranked — collecting fresh signals.
star history
Frustum PointNets is a 3D object detection system that combines 2D object detectors with 3D deep learning. The pipeline uses 2D bounding boxes from RGB images to define 3D frustum regions, then applies PointNet/PointNet++ networks on point clouds within those regions to perform 3D instance segmentation and amodal bounding box estimation. It works directly on 3D point clouds without voxelization, leveraging coordinate normalization techniques for improved learning.
Frequently asked
- What is charlesq34/frustum-pointnets?
- PointNet-based deep learning system for 3D object detection from RGB-D point clouds.
- Is frustum-pointnets open source?
- Yes — charlesq34/frustum-pointnets is open source, released under the Apache-2.0 license.
- What language is frustum-pointnets written in?
- charlesq34/frustum-pointnets is primarily written in Python.
- How popular is frustum-pointnets?
- charlesq34/frustum-pointnets has 1.7k stars on GitHub.
- Where can I find frustum-pointnets?
- charlesq34/frustum-pointnets is on GitHub at https://github.com/charlesq34/frustum-pointnets.