Stars
KITTI Object Visualization (Birdview, Volumetric LiDar point cloud )
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
OpenMMLab's next-generation platform for general 3D object detection.
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking (CVPR 2023)
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
[Lumina Embodied AI Community] 具身智能技术指南 Embodied-AI-Guide
Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"
A Comprehensive Framework for Visual SLAM Systems and Datasets
Awesome Papers about Autonomous Ground Robot System in Unstructured Off-Road Environments
Pointcloud Ground Segmentation: python binding of url-kaist/TRAVEL
[CVPR2025] From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting
VT&R3 is a C++ implementation of the Teach and Repeat navigation framework. It enables a robot to be taught a network of traversable paths and then closely repeat any part of the network.
[ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process
Code repository for Ground Mobile Robot Traversable Area Recognition Based on 3D CNN and Attention Mechanism
An advanced terrain-mapping robot designed to traverse various landscapes, including hills and valleys, to create detailed 3D mesh topology maps
STEPP: Semantic Traversability Estimation using Pose Projected features
This project is supporting code for the book of Robot SLAM Navigation Core Technology and the Actual Combat.
Perform vision based target tracking, 6DOF pose estimation, using single 2d camera. Created augmented reality visualization of visual target.
AnyLoc: Universal Visual Place Recognition (RA-L 2023)
Robot-centric elevation mapping for rough terrain navigation
Elevation Mapping on GPU.
GEM: Online Globally consistent dense elevation mapping for unstructured terrain.
Official Code Repository for La-MAML: Look-Ahead Meta-Learning for Continual Learning"