Open-source code for Paper: Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments

[IROS2024] GV-Bench: A geometric verification benchmark targeting long-term loop closure detection.

GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization

[ECCV 2024] GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time

Code for SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting built on gsplat codebase.

Effective and Reliable Pose Tracking for Mobile Robots Based on Lightweight and Compact Polygon Maps

3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt.

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

Continuous preintegration

Odometry application of the accurate distance field based on Gaussian Processes

Interactive Distance Field Mapping and Planning to Enable Human-Robot Collaboration

[ECCV 2024] SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

ROS implementation of DWA(Dynamic Window Approach) Planner

3D Gaussian Splatting Papers Relating to Large-Scale Scene.

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

A MultiModal Mapping (M2Mapping) Framework for LiDAR-Visual Systems

3D Reconstruction with Spatial Memory

Extending the Robustness of LiDAR SLAM to Geometrically Degenerate Scenarios

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

code for Mesh R-CNN, ICCV 2019

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

(IROS2024) STAIR: Semantic-Targeted Active Implicit Reconstruction

This project is used for lidar point cloud undistortion.

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Attention-based Deep Reinforcement Learning-based Autonomous Robot Exploration Planner in ROS

Undistorted Depth Support for ScanNet

a Multi-LiDAR dataset on Extreme Mapping Scnarios

Photo-realistic mapping of dynamic urban areas