Eaphan/GLENet
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [IJCV2023]
This project helps automotive engineers and researchers improve the accuracy of 3D object detection in self-driving systems. It takes raw 3D sensor data (like LiDAR point clouds) along with existing object labels, identifies the uncertainty in those labels, and then outputs more robust object detection models. Autonomous vehicle developers can use this to make their object detection systems more reliable.
189 stars. No commits in the last 6 months.
Use this if you need to build or enhance 3D object detection systems for autonomous driving and want to account for the inherent uncertainties in training data labels to achieve better real-world performance.
Not ideal if you are working with 2D image data or do not have access to 3D point cloud datasets like KITTI or Waymo.
Stars
189
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Eaphan/GLENet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.