Projects sharing features with EasyMocap

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

OpenCVSharp is a .NET library that wraps native OpenCV functions, providing C# developers with access to OpenCV's computer vision capabilities through an API that mirrors the native C/C++ style. It serves as a managed wrapper for image processing, feature detection, object detection, and image manipulation tasks, while also handling automatic disposal of unmanaged OpenCV resources like Mat objects to prevent memory leaks in .NET applications. The library enables keypoint detection and descriptor extraction using algorithms such as AKAZE, BRISK, or FAST, with brute-force or FLANN-based matchin

GoCV is a computer vision library and Go language binding for OpenCV. It serves as an image processing toolkit and deep learning inference engine, providing programmatic access to a wide range of algorithms for image manipulation, object detection, and video analysis. The project differentiates itself through high-performance native bindings and hardware acceleration. It utilizes a foreign function interface to map Go calls to C++ functions and includes a hardware-agnostic backend dispatch to route neural network tasks to computation engines such as CUDA and OpenVINO. The library covers a br

Kalibr is a software suite for multi-camera calibration and visual-inertial parameter estimation. It provides a mathematical framework for determining intrinsic and extrinsic parameters across multiple cameras and calculating the spatio-temporal offsets between cameras and inertial measurement units. The project features a non-linear least-squares optimizer to minimize reprojection and inertial errors. It includes specialized tools for rolling-shutter camera calibration to estimate projection and distortion parameters for sensors that capture images row-by-row. The system covers a broad rang

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

This is an open-source autonomous driving perception pipeline that processes camera and lidar sensor data to detect, track, and fuse objects in real-world driving environments. The project integrates an end-to-end perception workflow combining sensor calibration, deep learning object detection, Kalman filter tracking, and sensor fusion for robust scene understanding. The pipeline includes camera calibration tools to remove lens distortion from raw images, deep learning model training for object classification and detection, and multi-object tracking using Kalman filters with data association

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

COLMAP is a 3D scene reconstruction suite and C++ geometry library that implements a full structure-from-motion pipeline. It functions as a GPU-accelerated photogrammetry tool and multi-view stereo framework designed to produce dense 3D geometry and watertight meshes from collections of 2D images. The project distinguishes itself through hardware-accelerated feature extraction and a modular camera modeling system that supports perspective, fisheye, and equirectangular lens types. It employs vocabulary tree image retrieval to efficiently identify similar images in large datasets and provides P

FreeMoCap is an open-source markerless motion capture system that reconstructs 3D human pose from video. It uses a multi-camera setup with ChArUco board calibration to accurately triangulate body landmarks, and it also supports single-camera recording for simpler captures. The system outputs skeleton joint data and generates interactive Jupyter notebooks for each recording, enabling users to explore and analyse motion data directly. Built around hardware-synchronised video capture and MediaPipe-based 2D pose detection, FreeMoCap supports both calibrated multi-camera recording and real-time 2D

Champ is a generative vision system and controllable image-to-video generator designed for human image animation. It uses a diffusion-based video synthesizer and 3D parametric guidance to transform a single reference image into a consistent sequence of motion based on external driving data. The framework distinguishes itself through a human pose transfer system that employs 3D body parametric extraction and coordinate-space alignment. This allows the model to map motion from a driving video to a reference person by adjusting for body scales and camera perspectives using depth and semantic con

Gyroflow is a gyroscope video stabilization software and IMU telemetry processor designed to remove camera shake from video files. It functions as a hardware-accelerated video renderer and lens calibration tool, utilizing embedded or external gyroscope and accelerometer data to perform pixel-level stabilization. The system is distinguished by its ability to integrate with professional non-linear video editing software via plugins, allowing stabilization to be applied directly to timelines without transcoding original footage. It supports diverse telemetry ingestion from camera brands, flight

Kornia is a differentiable computer vision library and cross-framework tensor vision toolset. It implements vision operations as differentiable tensors to enable integration into deep learning pipelines and supports the transpilation of operations across PyTorch, TensorFlow, JAX, and NumPy. The project provides specialized toolsets for geometric vision and stereo depth, including algorithms for 3D scene reconstruction, camera calibration, and pose estimation. It further distinguishes itself as a differentiable image augmentation framework, applying random geometric and color transformations w

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

This project is a collection of optional, community-contributed algorithms and specialized vision tools that extend the core OpenCV framework. It serves as a comprehensive library of extra modules for computer vision research, providing advanced toolsets for image processing, visual data analysis, and object detection. The library includes specialized frameworks for augmented reality tracking, biometric face recognition, and three-dimensional pose estimation. It provides distinct capabilities for identifying AR markers, tracking 3D object silhouettes, and performing neural network vulnerabili

openMVG is a computer vision geometry library and toolkit for multiple view geometry. It serves as a framework for structure from motion and 3D scene reconstruction, providing the tools necessary to recover 3D point clouds and camera poses from collections of 2D images. The library implements both global and incremental structure-from-motion pipelines. It uses geometric algorithms to calculate camera pose estimation and image localization, employing Levenberg-Marquardt bundle adjustment to refine 3D coordinates and camera parameters by minimizing reprojection error. The project covers a broa

SensorsCalibration is a toolkit for computing the intrinsic and extrinsic parameters of cameras and LiDAR sensors in automotive environments. It provides tools for calculating internal camera focal properties, aligning LiDAR point clouds to 2D camera images, and determining the spatial transformations between multiple sensors and the vehicle coordinate system. The project includes a targetless calibration framework that aligns sensors to a vehicle by analyzing natural features in road environments without the need for specialized physical markers. It also supports factory calibration processe

The Intel RealSense SDK is a software development kit providing drivers and libraries for interfacing with depth cameras to capture color, depth, and infrared data streams. It includes a depth camera driver for device discovery and sensor configuration, a stereo vision library for computing depth maps and aligning frames, and a 3D point cloud generator to transform depth and infrared frames into spatial representations. The SDK distinguishes itself through on-chip depth calculation and stereo calibration, using internal vision processors to reduce host CPU load. It supports hardware-level str

Relativ is an open-source project for the development of custom virtual reality hardware, encompassing the mechanical design, electronics, and software interfaces required to build a headset from scratch. It provides the frameworks necessary for assembling devices using open-source electronics and firmware. The project integrates custom hardware with SteamVR through driver-based configurations, mapping device identifiers and display viewports to ensure rendered images align with physical secondary displays. It employs a combination of microcontroller-based inertial measurement unit polling fo

Open_vins is a visual-inertial odometry framework and SLAM system designed for robotic state estimation. It uses an Extended Kalman Filter to fuse high-frequency inertial sensor data with visual feature tracks to estimate the position and orientation of a moving device. The system features a sensor calibration suite for calculating intrinsic and extrinsic parameters, as well as temporal offsets between cameras and inertial measurement units. It includes a manifold interpolator that uses B-Spline curves over the special Euclidean group to produce smooth trajectory paths between discrete pose e

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.

Bodymovin is a motion graphics pipeline tool and plugin that exports After Effects animations into JSON files for native rendering on web and mobile platforms. It serves as a cross-platform animation bridge, converting complex vector motion designs into a portable Lottie format for use across different operating systems and frameworks. The project enables high-performance web animation by rendering motion graphics using SVG, Canvas, or HTML. It ensures consistent playback across diverse environments by converting dynamic expressions into static keyframes during the export process. The toolse

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

Rhubarb is an automated lip sync generator and phonetic speech analyzer that converts audio recordings into timed mouth-shape animation data. It identifies sounds and syllables within audio files to map them to specific visual mouth shapes, serving as an animation timing exporter for external character animation software. The tool utilizes a language-independent phonetic recognizer to process speech regardless of the spoken language. To increase accuracy, it supports dialogue-guided recognition by using external text files to guide the phonetic analysis of specific spoken scripts. The system

This project is a Java-based toolkit that integrates the OpenCV computer vision library into the Processing creative coding environment. It provides a programming interface designed to facilitate the inclusion of real-time image analysis and computer vision algorithms within interactive art installations and visual design projects. The library distinguishes itself by wrapping low-level C++ routines into a managed environment, allowing users to perform complex visual tasks through a simplified interface. It supports high-performance operations by sharing raw pixel data between the host environ

This project is a scientific computing framework for the .NET ecosystem, providing a comprehensive suite of libraries for numerical analysis, statistics, and mathematical optimization. It serves as a foundational toolkit for developing applications in machine learning, digital signal processing, and computer vision. The framework provides specialized toolkits for training and deploying predictive models, including neural networks, support vector machines, and decision trees. It further distinguishes itself with deep integrations for real-time visual analysis, such as object tracking and facia

JavaCV provides a Java-based interface for native computer vision and video processing libraries. It functions as a wrapper for native vision libraries, allowing Java applications to perform image analysis, object detection, and video stream processing. The project integrates comprehensive computer vision capabilities, including facial recognition, image segmentation, and optical flow analysis for motion tracking. It also provides tools for hardware geometry calibration and projector-camera alignment to ensure accurate spatial representation. The system covers high-performance media renderin

This project is a ROS2 depth camera driver that streams synchronized RGB, depth, infrared, and IMU data from Intel RealSense sensors as ROS2 topics. It functions as a managed camera interface using lifecycle nodes with explicit state transitions to ensure deterministic startup and shutdown within robotic systems. The driver includes an RGBD perception pipeline that aligns depth to color and generates 3D point clouds for spatial analysis. It features a depth camera calibration tool that provides ROS2 services for reading and writing on-device calibration and safety configuration parameters. T