jonathsch/lidar-synthesis
Official implementation of the ITSC 2023 paper "LiDAR View Synthesis for Robust Vehicle Navigation Without Expert Labels"
This project helps self-driving car developers and researchers create diverse training data for their navigation models. It takes existing LiDAR scans from safe driving scenarios and generates new, synthetic LiDAR point clouds from dangerous or hard-to-collect viewpoints. The output is augmented LiDAR data that improves the robustness of autonomous vehicle navigation systems.
No commits in the last 6 months.
Use this if you need to enhance the training datasets for self-driving car navigation models with synthetic LiDAR data, especially for hazardous driving scenarios.
Not ideal if you are looking for solutions that use only camera-based vision or require extensive expert human annotations for training data.
Stars
18
Forks
1
Language
Python
License
MIT
Category
Last pushed
May 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/jonathsch/lidar-synthesis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
isl-org/Open3D
Open3D: A Modern Library for 3D Data Processing
cvg/Hierarchical-Localization
Visual localization made easy with hloc
gmberton/CosPlace
Official code for CVPR 2022 paper "Rethinking Visual Geo-localization for Large-Scale Applications"
Vincentqyw/image-matching-webui
🤗 image matching webui
cvg/glue-factory
Training library for local feature detection and matching