An open source platform for visual-inertial navigation research.

ROS Wrapper for Intel(R) RealSense(TM) Cameras

Real-time dense scene reconstruction with SLAM3R

Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians

Official Repo For IEEE RAL 2024 Accepted paper "Fast-Poly"

Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models

Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

spatio-temporal-SEmantic Environment REPresentation for robots in an agricultural context

Evaluation of Visual Semantic Navigation Models in Real Robots

Official Implementation of Driv3R

[ICML2024] Official code for GaussianPro: 3D Gaussian Splatting with Progressive Propagation

Code for the Molmo Vision-Language Model

Official implementation for "CLIP-ReID: Exploiting Vision-Language Model for Image Re-identification without Concrete Text Labels" (AAAI 2023)

MACVO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry

Fixed Nav2 Wavefront Frontier Exploration

Package for auto exploring frontiers with ROS 2 Humble / Iron

From Coarse to Fine: Robust Hierarchical Localization at Large Scale with HF-Net (https://arxiv.org/abs/1812.03506)

[T-RO 2024] FALCON: Fast Autonomous Aerial Exploration using Coverage Path Guidance.

[NeurIPS 2024] L4GM: Large 4D Gaussian Reconstruction Model

[ECCV 2024] UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

End-to-End SLAM with camera calibration, monocular prior integration and dense Rendering

[arXiv'24] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

EfficientLO-Net: Efficient 3D Deep LiDAR Odometry (PAMI 2022)

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

Code for Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking

OVExp: Open Vocabulary Exploration for Object-Oriented Navigation

Official code for the OpenNav: Efficient Open Vocabulary 3D Object Detection for Smart Wheelchair Navigation - ACVR Workshop at ECCV'24

Awesome Monocular 3D detection