RGBD-inertial mode and its ROS interface was added to ORB_SLAM3. Two ROS interfaces Mono_inertial and Stereo_inertial were provided. Modified the loading vocabulary in a faster binary way.

Visual localization made easy with hloc

[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

This package provides localization in a pre-built map using ICP and odometry (or the IMU measurements).

KAN-based NeRF

Implementation of E-NeRF: Neural Radiance Fields from a Moving Event Camera (https://arxiv.org/abs/2208.11300). Simulated dataset: https://vision.in.tum.de/research/enerf

[CVPR'24] LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

[CVPR 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

Effectively Detecting Loop Closures using Point Cloud Density Maps

Deep Patch Visual Odometry

[ICRA 2024] Towards Large-Scale Incremental Dense Mapping using Robot-centric Implicit Neural Representation

3D高斯论文，持续更新，欢迎交流讨论。

[IROS 2024] MM3DGS SLAM: Multi-modal 3D Gaussian Splatting for SLAM Using Vision, Depth, and Inertial Measurements

The official repository of Compact 3D Gaussian Representation for Radiance Field

Point cloud map evaluation library for the FusionPortable dataset. Metrics include Mean Map Entropy (MME), RMSE, Accuracy(mean error), Precision(standard deviation), completeness(overlap ratio), ch…

Bag process and evalutaion tools for SLAM research

[CVPR 2024] Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras

Voxblox-based Pose graph optimization

The repository provides code associated with the paper VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation (ICRA 2024)

3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation (CVPR 2024)

Neural Graph Mapping for Dense SLAM with Efficient Loop Closure

SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System(CVPR2024)

VOLDOR-SLAM is a real-time dense-indirect SLAM system takes dense optical flows as input that supports monocular, stereo and RGB-D video sequence.

📍PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency [TRO' 24]

[ECCV 2024] RGBD GS-ICP SLAM

This is a unofficial fork of OpenVSLAM (https://github.com/xdspacelab/openvslam)

Full-python LiDAR SLAM using ICP and Scan Context

(ECCV2024)ADMap: Anti-disturbance framework for reconstructing online vectorized HD map

[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM