DCReg: Decoupled Characterization for Efficient Degenerate LiDAR Registration

Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Spatial Sparse Convolution Library

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Implementation of the Go-ICP algorithm for globally optimal 3D pointset registration

Patchwork++: Fast and robust ground segmentation method for 3D LiDAR scans. @ IROS'22

Powerful menu bar manager for macOS

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

This repository provides implementation of an incremental k-d tree for robotic applications.

Efficient and parallel algorithms for point cloud registration [C++, Python]

Robotics with GPU computing

深度学习经典、新论文逐段精读

X-SAM: From Segment Anything to Any Segmentation (AAAI2026)

Python SDK for OpenCyberGlove 🧤

Official PyTorch implementation of BiTrack

HEDNet (NeurIPS 2023) & SAFDNet (CVPR 2024 Oral)

The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.

CoTracker is a model for tracking any point (pixel) on a video.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

A high-throughput and memory-efficient inference and serving engine for LLMs

ROS package to fuse together IMU and wheel encoders in an EKF. Implemented in both C++ and Python. C++ version runs in real time.

Vehicle State Estimation using Error-State Extended Kalman Filter

A 3DGS framework for omni urban scene reconstruction and simulation.

国内首个占据栅格网络全栈课程《从BEV到Occupancy Network，算法原理与工程实践》，包含端侧部署。Surrounding Semantic Occupancy Perception Course for Autonomous Driving (docs, ppt and source code) 在线课程主页：http://111.229.117.200:8100/ (作者独立搭建)

A C++ port of the Python module under the same name

Implementation of papers in 100 lines of code.

🦉 Data Versioning and ML Experiments

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch