Captain

palmier-pro. macOS video editor built for AI

Global-LVBA. Global LiDAR-Visual Bundle Adjustment

AlohaMini. Open-Source Dual-Arm Mobile Robot with Motorized Lift

XLeRobot. XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

nunif. Misc; latest version of waifu2x; 2D video to stereo 3D video conversion

LIV_handhold. Hardware-synchronized device for FAST-LIVO (Handheld & UAV).

3dgs-compression-survey. An open survey on 3D Gaussian Splatting compression methods

minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

Luminance-GS. 🌕 [CVPR 2025] Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment

alpamayo. NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.

GaussianSplats3D. Three.js-based implementation of 3D Gaussian splatting

ReAct. [ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

FAST-LIVO2. FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

RAP. 🎤 Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching [ECCV 26]

Chat_input_widget. TypeScript

FSDrive. [NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"

SeqGrowGraph. [ICCV 2025] Official implementation for "SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions"

nanochat. The best ChatGPT that $100 can buy.

unreal-mcp. Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

MVHumanNet_plusplus. Python

awesome-public-datasets. A topic-centric list of HQ open datasets.

HunyuanWorld-Voyager. Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

YouTube-channel. Posts related to my YouTube videos

PGSR. [TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

COB-GS. COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting

ASAP. [RSS 2025] "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"

OpenYOLO3D. [ICLR 2025 (Oral 📢) ] Our OpenYOLO3D model achieves state-of-the-art performance in Open Vocabulary 3D Instance Segmentation on ScanNet200 and Replica datasets with up ∼16x speedup compared to the best existing method in literature.

FreePoint. [CVPR'24] FreePoint: Unsupervised Point Cloud Instance Segmentation

dgm. Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents

3dgrut. Ray tracing and hybrid rasterization of Gaussian particles

awesome-node-based-uis. A curated list with resources about node-based UIs

continue. open-source coding agent

OpenHands. 🙌 OpenHands: AI-Driven Development

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

bambot. Play with open source, low-cost AI robots with ease 🤖

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

DeepSeek-V3. Python

usdchat. usdchat is a conversational bot that lets you interact with USD Stage using natural language.

GS-LIVO. C++

LuisaCompute. High-Performance Rendering Framework on Stream Architectures

trimesh. Python library for loading and using triangular meshes.

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

Point-cloud-registration. 点云配准入门知识

VINS-Mono. A Robust and Versatile Monocular Visual-Inertial State Estimator

Hierarchical-Localization. Visual localization made easy with hloc

gaussian-splatting-lightning. A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

pyslam. pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

lift-splat-shoot. Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

e2e-parking-carla. Python

gaussian-opacity-fields. [SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes

opentracker-docker. Easy, customizable & small docker image for the opentracker project.

CoDA_NeurIPS2023. Official code for NeurIPS2023 paper CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection and TPAMI 2025 paper CoDAv2

CUDA_radix_sort. implementation of floating-point radix sorting based on CUDA

gaustudio. A Modular Framework for 3D Gaussian Splatting and Beyond

GaussianOcc. (ICCV 2025) GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting

sam_road. Segment Anything Model for large-scale, vectorized road network extraction from aerial imagery. CVPRW 2024

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

GeoGaussian. GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering

AddMeshPassPlugin. C++

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

img2img-turbo. One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

SceneViewExtensionTemplate. Unreal Engine 5 plugin template for adding custom rendering pass to the engine with a SceneViewExtension

hierarchical-3d-gaussians. Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

Gaussian-SLAM. Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting

Gaussian-Splatting-Monitor. Monitor Gaussian Splatting additional real-time viewable and differentiable outputs

U-KAN. [AAAI' 25] U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

SceneScape. Official Pytorch Implementation for "SceneScape: Text-Driven Consistent Scene Generation"

realmdreamer. Code for RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion [3DV 2025]

TopoNet. [Accepted at SCIENCE CHINA Information Sciences 2026] Graph-based Topology Reasoning for Driving Scenes

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

GaussianDreamer. [CVPR 2024] GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models

splat. WebGL 3D Gaussian Splat Viewer

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

End-to-end-Autonomous-Driving. [IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

tdmpc2. Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

GoMVS. [CVPR'24]🦿GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo

MTR. MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.

DocsGPT. Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

GVINS. Tightly coupled GNSS-Visual-Inertial system for locally smooth and globally consistent state estimation in complex environment.

webtorrent-desktop. ❤️ Streaming torrent app for Mac, Windows, and Linux

api.

HITNET-Stereo-Depth-estimation. Python scripts for performing stereo depth estimation using the HITNET Tensorflow model.

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.

bevfusion. [ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

deep_sort. Simple Online Realtime Tracking with a Deep Association Metric

street-fighter-ai. This is an AI agent for Street Fighter II Champion Edition.

whisper.cpp. Port of OpenAI's Whisper model in C/C++

so-vits-svc. SoftVC VITS Singing Voice Conversion

Digital_Life_Server. Yet another voice assistant, but alive.

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

stable-diffusion-webui. Stable Diffusion web UI

Real-Time-Voice-Cloning. Clone a voice in 5 seconds to generate arbitrary speech in real-time

emqx. The most scalable and reliable MQTT broker for AI, IoT, IIoT and connected vehicles

ETEngine. Realtime 3D Game-Engine with a focus on space sim. Written in C++ 14

PhysX. NVIDIA PhysX SDK

ue4-rts. Real-time strategy plugin and showcase for Unreal Engine 4.

QGIS. QGIS is a free, open source, cross platform (lin/win/mac) geographical information system (GIS)

asammdf. Fast Python reader and editor for ASAM MDF / MF4 (Measurement Data Format) files

rviz. ROS 3D Robot Visualizer

cycles. The Cycles Render Engine - official mirror

ODE. Open Dynamics Engine (ODE) github mirror from https://bitbucket.org/odedevs/ode

ros2. The Robot Operating System, is a meta operating system for robots.

Crystal. Legend of Mir 2 - Official Public Crystal Source

mir2x. open source MMORPG game

cnpy. library to read/write .npy and .npz files in C/C++

lanenet-lane-detection. Unofficial implemention of lanenet model for real time lane detection

KawaiiPhysics. KawaiiPhysics : Simple Bone Physics for UnrealEngine 4 & 5

LittleBigMouse. DPI Aware mouse move across screens

DLSS. NVIDIA DLSS is a new and improved deep learning neural network that boosts frame rates and generates beautiful, sharp images for your games

echo. A New Cross-Platform 2D 3D Game Engine

colmap. COLMAP - Structure-from-Motion and Multi-View Stereo

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

auto. autopilot

OpenDRIVE. Unreal Engine OpenDRIVE plugin

MIDIVisualizer. A small MIDI visualizer tool, using OpenGL

anything_about_game. A wonderful list of Game Development resources.

VideoCapture. Windows Video Audio Capture, Save BMP file

libdshowcapture. Free and Open Source C++11 Library for capturing DirectShow video/audio devices on windows.

ZeloEngine. Game Engine in C++/OpenGL/Lua

awesome-tensorflow-lite. An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.

Ultra-Fast-Lane-Detection. Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

cpp-httplib. A C++ header-only HTTP/HTTPS server and client library

raymarching-workshop. An Introduction to Raymarching

PhotorealismEnhancement. Code & Data for Enhancing Photorealism Enhancement

RayTracingInVulkan. Implementation of Peter Shirley's Ray Tracing In One Weekend book using Vulkan and NVIDIA's RTX extension.

openISP. Image Signal Processor

openpilot. openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

OpenCat-Quadruped-Robot. An open source quadruped robot pet framework for developing Boston Dynamics-style four-legged robots that are perfect for STEM, coding & robotics education, IoT robotics applications, AI-enhanced robotics application services, research, and DIY robotics kit development.

openDog. CAD and code for each episode of my open source dog series

RobotX. All the things for RobotX

map. AD Map access library

mav_active_3d_planning. Modular framework for online informative path planning.

webots. Webots Robot Simulator

habitat-sim. A flexible, high-performance 3D simulator for Embodied AI research.

netron. Visualizer for neural network, deep learning and machine learning models

esmini. a basic OpenSCENARIO player

simulator. A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles

curv. a language for making art using mathematics

opendriveparser. OpenDRIVE Map parser

path-following-control. 关于路径跟踪控制实现的项目

ompl. The Open Motion Planning Library (OMPL)

path_planner. Hybrid A* Path Planner for the KTH Research Concept Vehicle

Lane-and-Vehicles-Detection. This repository contains works on a computer vision software pipeline built on top of Python to identify Lanes and vehicles in a video. This project is not part of Udacity SDCND but is based on other free courses and challanges provided by Udacity. It uses Computer vision and Deep Learrning Techniques. Few pipelines have been tried on SeDriCa, IIT Bombay.

ai_for_robotics. Visualizations of algorithms covered in Sebastian Thrun's excellent Artificial Intelligence for Robotics course on Udacity.

opencv. Open Source Computer Vision Library

PyAdvancedControl. Python codes for advanced control

MATLABRobotics. MATLAB sample codes for mobile robot navigation

scipy. SciPy library main repository

PythonRobotics. Python sample codes and textbook for robotics algorithms.

GeometricTools. A collection of source code for computing in the fields of mathematics, geometry, graphics, image analysis and physics.

apollo. An open autonomous driving platform

carla. Open-source simulator for autonomous driving research.

Deep_reinforcement_learning_Course. Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch

grpc. C++ based gRPC (C++, Python, Ruby, Objective-C, PHP, C#)

AssetStudio. AssetStudio is a tool for exploring, extracting and exporting assets and assetbundles.

manim. Animation engine for explanatory math videos

terrain-erosion-3-ways. Three Ways of Generating Terrain with Erosion Features

ant-design. An enterprise-class UI design language and React UI library

blender. Official mirror of Blender

cpuminer. CPU miner for Litecoin and Bitcoin

cpuminer. CPU miner for bitcoin

dogecoin. very currency

Overload. 3D game engine with lua scripting

CustomComputeShaders. The minimal source code for adding and using a custom compute shader in Unreal Engine 4

wren. The Wren Programming Language. Wren is a small, fast, class-based concurrent scripting language.

mapgen4. Mapgen4 procedural wilderness map generator

protongraph. Experimental node-based software for procedural content generation

standardese. A (work-in-progress) nextgen Doxygen for C++

loli_profiler. Memory instrumentation tool with CI and AI support for android app&game developers.

vk_optix_denoise. Denoising a Vulkan ray traced image using OptiX denoiser

vk_mini_path_tracer. A beginner-friendly Vulkan path tracing tutorial in under 300 lines of C++.

GLSL-PathTracer. A toy physically based GPU path tracer (C++/OpenGL/GLSL)

ToyPathTracer. Toy path tracer for my own learning purposes (CPU/GPU, C++/C#, Win/Mac/Wasm, DX11/Metal, also Unity)

VulkanSamples. Vulkan Samples

Vulkan-Samples. One stop solution for all Vulkan samples

Dora-SSR. A game engine for rapid development across devices, featuring a built-in Web IDE with intuitive toolchain.

flex. The Fast Lexical Analyzer - scanner generator for lexing in C and C++

SpartanEngine. A game engine with a fully bindless, GPU-driven renderer featuring real-time path-traced global illumination, hardware ray tracing, and a physics simulation running at 200Hz, built over 10+ years of R&D

vulkan-tutorial. This is a series of tutorials on Vulkan, include all example projects which step by step.

X-PostProcessing-Library. Unity Post Processing Stack Library | Unity引擎的高品质后处理库

gin. Gin is a high-performance HTTP web framework written in Go. It provides a Martini-like API but with significantly better performance—up to 40 times faster—thanks to httprouter. Gin is designed for building REST APIs, web applications, and microservices.

awesome-ray-tracing. Curated list of ray tracing resources

rtxON. Simple Vulkan raytracing tutorials

editor. 一个游戏编辑器

QWidgetDemo. Qt编写的一些开源的demo，预计会有100多个，一直持续更新完善，代码简洁易懂注释详细，每个都是独立项目，非常适合初学者，代码随意传播使用，拒绝打赏和捐赠，欢迎留言评论！公众号：Qt实战/Qt入门和进阶/Qt教程

DirectX-Graphics-Samples. This repo contains the DirectX Graphics samples that demonstrate how to build graphics intensive applications on Windows.

O266player. C

VQEngine. Multi-threaded DirectX12 renderer w/ HDR, PBR & Multi-monitor support

ShadowFX. DirectX 11 and 12 library that provides a scalable and GCN-optimized solution for deferred shadow filtering

HoudiniEngineForUnreal-v2. Houdini Engine Plugin for Unreal Engine 4 - Version 2

haxe. Haxe - The Cross-Platform Toolkit

sokol. minimal cross-platform standalone C headers

VulkanDemos. Some simple vulkan examples.

OpenFBX. Lightweight open source FBX importer

spot-sdk. Spot SDK repo