The tarnished will soon return.
PointPillars_MultiHead_40FPS. A REAL-TIME 3D detection network [Pointpillars] compiled by CUDA/TensorRT/C++.
307MIT-18.03-ode-notes. MIT 18.03 微分方程(Differential Equations)中文笔记
103OpenPCDet. OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
43Lidardet. A rewrite verson of Lidar detection deeplearning framework (PointPillars) for multi device fast applications ((pc train and vehicle inference)).
30CUDA-MatMul-Practice. Cuda
19Pointcloud-Viewer. A light and easy to change point cloud / lidar visualization tool, and supports multiple formats of data types.
11pointcloud-notes. 一些点云处理笔记
9numiou. A light-weight and numpy-only rotated intersection over union (IoU) library for object detection.
9Open3d_Viewer. Useful 3d lidar visualization tool
2Correction_OBB. 通常,点云目标检测网络(如pointrcnn)出来的OBB与真实存在着些许误差,本仓库利用PCA配合BallTree算法对已知的OBB进行修正,效果喜人
2vectorlens. Multi-modal vector search demo for text + video, with a clean interactive CLI.
2cuFPS.example. A example of Furthest Point Sampling algorithm implementation on CUDA
1pyUKF. Unscented kalman filter (UKF) library in python that supports multiple measurement updates
1polyscope. A C++ & Python viewer for 3D data like meshes and point clouds
1cuda_torch.unique. A c++ and cuda implement scripts of torch.unique
1bevformer.clean. A clean-room BEVFormer-style camera-only 3D detection repository for nuScenes, written with explicit PyTorch code and without MMDetection3D/MMCV framework dependencies.
1