Projects sharing features with MichaelGrupp Evo

This project is a parallel simulation engine and molecular dynamics simulator designed to model the physical movements of atoms and molecules. It functions as an interatomic potential framework for calculating forces between particles and a materials analysis tool for computing thermodynamic, structural, and transport properties of solids and fluids. The engine is distinguished by its high-performance computing capabilities, utilizing spatial-domain decomposition and message-passing interface communication to distribute workloads across processors. It supports multi-backend GPU acceleration v

FAST-LIVO2 is a LiDAR-inertial odometry framework and factor-graph SLAM implementation designed for real-time robot localization and 3D mapping. It functions as a multi-sensor fusion pipeline and state estimator that integrates LiDAR, inertial, and camera inputs to track a robot's position and orientation. The system employs a tightly-coupled sensor fusion approach to maintain stable navigation, particularly in degraded environments. It utilizes a voxel-based 3D mapping tool to organize point clouds into volumetric grids, which optimizes memory usage and search speed during spatial reconstruc

webgl-fundamentals is a comprehensive educational resource and graphics tutorial for learning hardware-accelerated 2D and 3D rendering using the WebGL API. It serves as a structured 3D graphics curriculum and GPU programming reference, guiding users through the graphics pipeline from basic geometry to advanced rendering techniques. The project provides detailed guides on GLSL shader development, including the creation of vertex and fragment shaders. It specifically focuses on the implementation of real-time lighting models—such as directional, point, and spot lighting—and the application of s

This project is a technical guide and implementation library for advanced visual effects and hardware-accelerated animations using the Core Animation framework on iOS. It provides a comprehensive reference for creating high-performance motion graphics, custom graphic rendering, and the construction of 3D engines using perspective transforms and Z-axis manipulation. The collection distinguishes itself through a deep focus on GPU rendering optimization and graphics performance. It covers advanced strategies to maintain high frame rates, such as reducing offscreen rendering via shadow path optim

SmartCropper is a computer vision library and user interface component designed for automated document border identification and perspective-based image cropping. It provides a framework for detecting the edges of items such as ID cards and business cards to suggest crop boundaries and apply geometric transformations that flatten skewed images into front-facing views. The project features an interactive document scanner interface that allows for manual crop area adjustment. This is achieved through draggable anchor points and a magnifying glass tool for high-precision pixel alignment. The li

snabbt.js is a JavaScript motion framework and CSS transform animation library used to create high-performance animations for DOM elements. It functions as a 3D CSS animation engine and a matrix-based geometry toolkit for calculating precise translations, rotations, scales, and skews. The framework provides a user-driven animation controller that allows animation progress to be tied to manual user input rather than standard time-based playback. It enables the simulation of depth and perspective by animating HTML elements into three-dimensional shapes. The system covers motion orchestration t

This research framework provides a deep learning driving simulator and a multimodal data pipeline for autonomous vehicle research. It centers on the creation of synchronized autonomous vehicle datasets, which combine high-frequency vehicle telemetry with camera frames to train neural networks. The project implements a convolutional neural network trainer specifically designed to predict steering angles and vehicle transition states from visual data. It features generative capabilities, using autoencoders and transition models to synthesize driving environments and simulate future vehicle move

This code is a fork from LeGO-LOAM-BOR to migrate LeGO-LOAM algorithm to ROS2.

Remove then revert (IROS 2020)

YouTube | arXiv | Website | IEEE RA-L | Demonstrator

OverlapNet - Loop Closing for 3D LiDAR-based SLAM (chen2020rss)

Cartographer is a cross-platform robotics library and framework for simultaneous localization and mapping in 2D and 3D spaces. It functions as a real-time mapping engine that constructs environmental maps while tracking a device's position and orientation using continuous sensor data processing. The system implements real-time SLAM to generate precise maps for autonomous navigation. It utilizes a localization system that determines a device's state within a mapped environment across different hardware platforms and sensor configurations. The framework covers spatial estimation through non-li

KISS-SLAM is a simple, robust, and accurate 3D LiDAR SLAM system that just works.

LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain

LIO-SAM is a lidar inertial SLAM framework and tightly-coupled sensor fusion pipeline. It functions as a factor graph optimization engine that combines lidar scans and inertial measurement unit data to build 3D point cloud maps and estimate robot trajectories. The system integrates global position factors to align local coordinates with real-world data. It employs loop closure detection to identify previously visited locations, creating constraints in the optimization graph to correct accumulated global drift. The framework covers lidar inertial odometry, point cloud processing, and trajecto

This project is a declarative visualization library and geospatial framework designed for rendering large-scale data sets within web browsers. It functions as a high-performance graphics engine that leverages hardware acceleration to display complex 2D and 3D visual layers, enabling the visualization of millions of data points through a structured, component-based syntax. The framework distinguishes itself through its ability to synchronize custom data visualizations with third-party mapping platforms. By managing camera states and coordinate systems, it allows developers to overlay high-perf

Folium is a Python library that builds interactive Leaflet.js maps directly from Python data structures, enabling geographic data visualization in Jupyter notebooks or as standalone HTML pages. It creates maps centered on given coordinates with configurable zoom, tiles, and dimensions, and supports embedding those maps inside web routes for serving in browsers. The library provides a comprehensive set of tools for data-driven map creation, including choropleth maps that bind tabular data to geographic geometries, colormap application to markers and polygons, and GeoJSON data overlay and visua

Rainmeter is a Windows desktop widget engine that renders customizable skins and interactive widgets directly on the desktop, supporting live data feeds and user interaction. It functions as a desktop customization platform and skin authoring framework, allowing users to create widgets by defining data sources and visual elements with full style and layout control. The engine includes a Lua scripting runtime for extending widget functionality with custom logic and data processing, and provides a plugin SDK with a C/C++ API for building native plugins that add new data sources or rendering capa

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

AgiBot-World is a suite of software pipelines and tools designed for robotic policy training, dataset standardization, embodiment transfer, and performance benchmarking. It provides infrastructure for developing bimanual manipulation policies using foundation models and human-reference trajectory data. The project features a robot embodiment transfer suite that adapts pre-trained models to different robot bodies without requiring new multi-embodiment training data. It also includes a specialized evaluation framework for validating vision-language-action models through open-loop testing and ph

ORB_SLAM2 is a visual simultaneous localization and mapping system that tracks camera movement and builds 3D environments from image data. It functions as a real-time visual odometry tool and sparse 3D reconstructor, computing the position and orientation of a camera while generating a point cloud map of a physical space. The system utilizes a camera relocalization engine to identify a camera's position within a known map after tracking failure or system restarts. It incorporates a spatial tracker to enable the precise insertion and composition of virtual 3D objects into real-world planar reg

react-native-maps is a cross-platform map component and visualization library for embedding interactive maps within mobile applications on iOS and Android. It provides a declarative interface for managing geospatial user interfaces, allowing for the rendering of geographical data and location-based features. The library enables the visualization of spatial data through the placement of markers, the creation of custom callouts, and the drawing of polylines and polygons as map overlays. It supports interactive map navigation, including the ability to animate map regions and customize the visual

This project is an open-source 3D game engine designed for building high-fidelity games, simulations, and cinematic environments. It functions as a robotics simulation platform with native integration for ROS 2 to model robot controllers and sensors. The engine features a multi-threaded Forward+ physically based renderer that supports hardware-accelerated ray tracing and global illumination. The system is built on a modular extension architecture using Gems to add or replace features without modifying core binaries. It includes a native SDK for AWS cloud integration, enabling IAM authenticati

AndroidNote is a technical knowledge base and reference resource for Android development. It provides comprehensive guidance on application architecture, custom view development, and advanced graphics programming. The project is distinguished by its depth in visual implementation, covering pseudo-3D perspective projections via virtual cameras and complex 2D rendering using Bézier curves and PorterDuff color blending. It also provides detailed methodologies for app modularization and the management of internal libraries through private Maven repositories and JitPack. The reference surface ext

This project is a comprehensive CSS animation tutorial and a structured frontend animation course. It serves as a web motion learning resource designed to teach the implementation of visual transitions and animations within a browser. The resource provides a guide to CSS 3D animation, covering the rendering of three-dimensional scenes and depth. It includes instructions on motion design, ranging from scroll-triggered animations and sprite sheet animation to the creation of complex web interface animations. The material covers core capabilities such as manipulating element geometry, controlli