NVIDIA-AI-IOT/Lidar_AI_Solution
A collection of GPU-accelerated 3D object detection networks (PointPillars, CenterPoint, BEVFusion) for self-driving Lidar perception.
Not currently ranked — collecting fresh signals.
star history
This repository provides highly optimized Lidar AI solutions for autonomous driving, featuring GPU-accelerated deep learning networks for 3D object detection. It includes implementations of PointPillars, CenterPoint, and BEVFusion with custom CUDA kernels for sparse convolution, voxelization, and feature fusion. The project offers a standalone inference engine for 3D sparse convolutional networks independent of TensorRT, plus TensorRT-integrated solutions for camera-lidar BEV fusion. Pre/post-processing are optimized with CUDA kernels to maximize throughput on NVIDIA hardware.
Frequently asked
- What is NVIDIA-AI-IOT/Lidar_AI_Solution?
- A collection of GPU-accelerated 3D object detection networks (PointPillars, CenterPoint, BEVFusion) for self-driving Lidar perception.
- Is Lidar_AI_Solution open source?
- Yes — NVIDIA-AI-IOT/Lidar_AI_Solution is an open-source project tracked on heatdrop.
- What language is Lidar_AI_Solution written in?
- NVIDIA-AI-IOT/Lidar_AI_Solution is primarily written in C++.
- How popular is Lidar_AI_Solution?
- NVIDIA-AI-IOT/Lidar_AI_Solution has 1.9k stars on GitHub.
- Where can I find Lidar_AI_Solution?
- NVIDIA-AI-IOT/Lidar_AI_Solution is on GitHub at https://github.com/NVIDIA-AI-IOT/Lidar_AI_Solution.