分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.

符合nature论文学术表达和科研绘图的Skill

Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization Algorithm,Immune Algorithm, Artificial Fish Swarm Algorithm, Differential Evolution and TSP(Traveling sa…

GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

Frustum PointNets for 3D Object Detection from RGB-D Data

🤖 PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

Toolbox for quantitative trajectory evaluation of VO/VIO

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

GenZ-ICP: SOTA robust LiDAR odometry (IEEE RA-L 2025)

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

A LiDAR SLAM system that just works

🌟 SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations (ICRA 2023)

Python package for segmenting LiDAR data using Segment-Anything Model (SAM) from Meta AI.

Extending the Robustness of LiDAR SLAM to Geometrically Degenerate Scenarios

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

OpenPCDet for ROS noetic, docker image also provided

[IROS'22] MMFN: Multi-Modal Fusion Net for End-to-End Autonomous Driving

[ICRA 2022] The official repository for "LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition", In 2022 International Conference on Robotics and Automation (ICRA), pp. 221…

FRAME: Fast and Robust Autonomous 3D Point Cloud Map-Merging for Egocentric Multi-Robot Exploration

FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion

Livox simulation for Ubuntu18 and Gazebo 9, and can import 3 Ros messages: PointCloud, PointCloud2 and CustomMsg, they can be used in A-LOAM, Fast-LIO and so on.

Code release for CoRL'25 paper "Opal: Visibility-aware lidar-to-openstreetmap place recognition via adaptive radial fusion"

Image Super-Resolution Using Very Deep Residual Channel Attention Networks