Stars
[RAL 2024] OpenGraphs: Open-Vocabulary Hierarchical 3D Scene Graphs in Large-Scale Outdoor Environments
A system for building 3D Scene Graphs from sensor data in real-time
✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models
Visual Neuro-Symbolic Friction Learning for Off-road Navigation
Leveraging BEV Maps in LLMs for Robust Closed-Loop Driving
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
Unreal Engine Plugin to enable ROS Support
[RA-L] DRAGON: A Dialogue-Based Robot for Assistive Navigation with Visual Language Grounding
Multi-Scene Camera Pose Regression with Transformers
[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion
Enjoy the magic of Diffusion models!
a simple map generator based on ROS
[CVPR 2024🔥] Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization
The official implementation of "GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive Transformers" [European Conference on Computer Vision (ECCV) 2024]
[ICCV'25] GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization
[ECCV 2024] About The official implementation of the paper "Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network“.
[ISPRS P&RS'25] Official repository of the paper Cross-View Geo-Localization with Panoramic Street-View and VHR Satellite Imagery in Decentrality Settings.
Python package for the evaluation of odometry and SLAM
[ICCV'25] GS-LIVM: Real-Time Photo-Realistic LiDAR-Inertial-Visual Mapping with Gaussian Splatting
Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.
ROS 2 Navigation Framework and System
Source Code for CVPR 2024 paper: View From Above: Orthogonal-View aware Cross-view Localization
clash for windows汉化版. 提供clash for windows的汉化版, 汉化补丁及汉化版安装程序
[IROS 2024] [ICML 2024 Workshop Differentiable Almost Everything] MonoForce: Learnable Image-conditioned Physics Engine
SOTA fast and robust ground segmentation using 3D point cloud (accepted in RA-L'21 w/ IROS'21)
Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.