Projects sharing features with Relativ

DensePose is a 3D human pose estimation framework designed to map 2D image pixels to a 3D surface-based model of the human body in real time. It functions as a computer vision anatomical mapper that projects 2D visual data onto a 3D surface to create detailed anatomical representations. The system operates as an image-to-3D texture transfer engine, localizing 2D image annotations onto 3D models to apply photographic textures to digital human representations. It uses a surface-based body mapping method to associate human pixels in an RGB image with specific coordinates on a 3D body template.

OpenCat-Quadruped-Robot is a development framework and motion control API for building four-legged robots. It provides a comprehensive environment for quadruped robot development, featuring tools for locomotion gait design, inverse kinematics, and a layered control architecture that separates high-level intelligence from low-level motion. The project distinguishes itself as an embedded AI deployment tool, allowing users to train, quantize, and deploy machine learning models to vision modules for tasks such as object detection and visual target tracking. It further supports complex human-robot

AlphaPose is a deep learning pose estimation framework and PyTorch computer vision library designed for detecting and tracking human body, face, hand, and foot keypoints in images and videos. It provides a system for skeletal posture estimation and multi-person pose tracking. The project implements tools for three-dimensional human pose reconstruction, generating joint positions and body mesh shapes from two-dimensional image data. It also includes a multi-person pose tracker capable of maintaining the identity of multiple people across consecutive video frames. The framework covers a broad

This project is a pedagogical implementation of a hash table in C, built from scratch using open addressing and linear probing for collision resolution. It serves as a computer science algorithm demo, demonstrating how to construct a fundamental key-value store at a low level. The implementation covers the core operations of an associative array: inserting a key-value pair, looking up a value by its key, and deleting a pair. It uses a hash function to compute storage locations, maps hash values to array indices with the modulo operator, and resolves collisions by scanning sequentially through

This project is a content delivery network implementation that uses a web server and scripting language to cache content at the edge and reduce latency for end users. It functions as a distributed system designed to store backend responses on edge nodes and route incoming client requests through a proxy. The system utilizes custom request logic to handle edge caching strategies, including the delivery of stale content during origin failures. It implements request coalescing to merge simultaneous requests for the same resource into a single upstream call to prevent backend overload. The proje

Now even your pet rock can parse JSON.

This repository is a comprehensive collection of data structures and algorithms implemented in JavaScript, designed primarily as an educational resource for computer science study and technical interview preparation. It provides modular implementations of fundamental programming concepts, allowing developers to explore algorithmic logic and data organization through self-contained, verifiable code examples. The library distinguishes itself by pairing every implementation with formal Big O notation, providing predictable insights into time and space scaling requirements. Each algorithm is stru

An extremely lite-weight cache framework in Kotlin, demonstrating how cache works.

📦 A simplified example of a modern module bundler written in JavaScript

Learn how npm or Yarn v1 works.

This project is an open-source software development kit and framework for implementing the Matter smart home standard. It provides a universal IPv6-based application layer and a cluster-based data model to ensure interoperability between diverse smart home devices and controllers. The system is distinguished by its multi-transport network abstraction, which maps Bluetooth LE, Thread, and Wi-Fi implementations to a common layer. It includes specialized tooling for secure device commissioning via QR codes and NFC, as well as a comprehensive over-the-air firmware update system for distributing s

VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion reconstruction tool that predicts 3D joint positions from 2D video sequences using a temporal convolutional network to process body movement over time. The project includes a semi-supervised learning pipeline that improves pose accuracy by combining labeled datasets with unlabeled video data and projection consistency loss. It also features a video pose visualizer capable of rendering 3D skeleton reconstructions and 2D keypoints as overlays on original footage. The framework covers the

DeepLabCut is a deep learning toolkit for markerless 2D and 3D animal pose estimation. It functions as a motion tracking system that identifies anatomical keypoints on animals in video sequences without the need for physical markers. The framework utilizes transfer learning and a library of pre-trained weights to accelerate the training of networks for different species. It supports multi-individual identity tracking to maintain unique identities across video sequences and offers real-time pose detection for live video feeds. The system covers a broad range of computer vision capabilities, i

OpenVR is a software development kit and runtime that provides a unified API for accessing virtual reality hardware from multiple manufacturers. It abstracts vendor-specific headsets, controllers, and tracking systems into a common interface, enabling applications to work across different VR devices without requiring hardware-specific code. The SDK handles core VR operations including stereoscopic frame submission to a compositor, headset and controller tracking, and input binding that maps abstract application actions to physical device controls. The runtime is built around a modular driver

AR.js is a web-based augmented reality framework used to create immersive experiences directly in a browser using WebGL and WebRTC. It provides a cross-platform runtime that executes on mobile devices and head-mounted displays without requiring a dedicated application installation. The framework includes a marker-based engine for detecting physical patterns or barcodes to anchor digital overlays, a location-based tool for positioning entities via GPS coordinates, and a face tracking library for anchoring content to human facial features. It supports multi-marker simultaneous tracking, custom

VIBE is a 3D human pose estimation framework designed to reconstruct human body shapes and poses from video frames. It functions as a toolkit for predicting parameters of the SMPL human body model to generate 3D mesh sequences. The system includes a 3D motion data exporter to convert predicted pose sequences into standard 3D file formats for use in graphics and animation software. It also provides a structured training pipeline for preparing datasets and training models to estimate body shapes from images. Its capabilities cover computer vision for estimating body pose and shape, as well as

This project is a Java library for establishing raw serial port connections between Android devices and external hardware using USB host mode. It provides a communication bridge for interacting with microcontrollers and adapters without requiring root access. The library includes a device identification framework to detect and map serial hardware using vendor and product IDs. It features specialized driver implementations for chipsets such as CDC and FTDI to enable data exchange across different hardware standards. It covers hardware integration capabilities including device discovery, seria

This project is a 3D visual localization framework designed to determine a camera's exact position and orientation by matching 2D image features against a 3D reference model. It includes a structure-from-motion pipeline to reconstruct 3D scene geometry from unordered image sets, creating the necessary spatial maps for localization. The system employs a hierarchical coarse-to-fine localization approach. This process begins with a global-descriptor image retrieval system to identify candidate reference images from a large database and progresses through local feature matching to final 3D model

Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve

MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The

sam-3d-body is a machine learning framework for 3D human mesh recovery and pose estimation. It utilizes a 3D human mesh recovery model to reconstruct full-body meshes, including the body, hands, and feet, from a single image. The project implements a specialized extension of the Segment Anything Model to guide the extraction and refinement of human body shapes. This integration allows for prompt-guided mesh recovery, where 2D masks and keypoints constrain the inference of 3D pose and shape parameters. The system covers a range of computer vision capabilities, including 3D spatial alignment t

OpenTabletDriver is a user-mode graphics tablet driver and USB HID input manager that translates raw USB input from digitizer hardware into system cursor and pen events. It serves as a hardware abstraction layer that normalizes input from various tablet brands into a consistent API, providing a cross-platform pen interface with pressure and tilt sensitivity. The project distinguishes itself through a plugin-based architecture and a profile-based configuration system, allowing for custom filters, interpolators, and persistent hardware setups. It includes specialized tools for hardware driver d

EasyMocap is a markerless 3D human motion capture system that recovers body, hand, and face poses from single or multi-view video without physical markers or suits. It uses parametric body models like SMPL, SMPL-X, and MANO, and leverages mirror reflections to resolve depth ambiguity in single-view pose estimation, improving accuracy by computing mirror surface normals from vanishing points. The system distinguishes itself through mirror-assisted depth disambiguation, enabling accurate 3D pose reconstruction from a single RGB image or video that includes a mirror reflection. It also supports

stlink is a toolset for ARM Cortex-M flashing, firmware management, and debug server operations, with specific support for STM32 microcontrollers. It provides an ARM Cortex-M flash programmer for writing binary and hex files, an ITM trace logger for real-time instrumentation data, and a SWD/JTAG debug server. The project includes a graphical user interface for managing MCU firmware and exporting memory, as well as a remote server that allows external debuggers to control execution and inspect registers on target hardware. The toolset covers microcontroller memory management through flash era

esptool is a Python-based serial utility designed for flashing firmware, configuring hardware fuses, and provisioning Espressif system-on-chip devices. It functions as a serial firmware flasher and hardware provisioning tool that interacts with chips over a serial connection to enable program execution and device setup. The tool provides specialized capabilities for managing Espressif hardware, including the ability to set permanent electronic fuses to lock security settings and define hardware-level configurations. It also features a serial communication bridge that routes network traffic to