An open-source C++ toolkit for developing interactive medical image processing software by combining ITK and VTK.

A NASA-developed suite of open-source automated geodesy and stereogrammetry tools for processing stereo images into 3D terrain models and cartographic products.

An open-source Android media gallery that provides a privacy-focused alternative to Google Photos with optional LibrePhotos server integration for AI-powered search and face recognition.

An anime scene search engine that identifies the specific anime, episode, and timestamp of a screenshot using image vector search.

An open-source network video platform that unifies GB28181, ONVIF, and RTSP streams into a single browser-based management system with AI alerting support.

A Python toolbox for large-scale calcium and voltage imaging analysis, providing scalable algorithms for motion correction, source extraction, and spike deconvolution.

A ROS 2 package that processes raw camera images into a usable format for higher-level vision processing in robotics.

Tess4J is a Java JNA wrapper for the Tesseract OCR API that allows developers to extract text from various image formats and PDF documents.

A Python package that simplifies using Amazon Textract to extract text, tables, forms, and identity data from documents.

An AI fitness assistant that uses RTMPose for real-time pose detection and automatic exercise repetition counting via a webcam.

A computational pathology toolbox based on PyTorch that provides an end-to-end API for analyzing tissue images, from data loading to visualization.

EdgeYOLO is an anchor-free object detector optimized for real-time performance on embedded edge devices like Nvidia Jetson, supporting multiple deployment formats including TensorRT and RKNN.

A visual node editor for creating and prototyping OpenCV algorithms with live pipeline previews.

A fast hybrid vision transformer that uses structural reparameterization to achieve low-latency image classification on mobile devices.

A real-time multi-object tracking system written in C++ that implements ByteTrack, OC-SORT, Deep OC-SORT, and DeepSORT using YOLO and ONNX Runtime.

MobileOne provides PyTorch implementations of five ultra‑fast CNN backbones (S0‑S4) that achieve 71‑79 % ImageNet Top‑1 accuracy with ≤ 2 ms latency on an iPhone 12 Pro. The repo includes training‑ready and inference‑ready checkpoints, CoreML models for on‑device deployment, and an iOS benchmark app (ModelBench). Re‑parameterization fuses training‑time branches into a single fast network for inference.

Matrix3D is a unified photogrammetry model that performs pose estimation, depth prediction, and novel view synthesis to enable 3D reconstruction from single or few-shot unposed images.

A discrete denoising diffusion model for generating synthetic graphs and molecular structures using a Graph Transformer architecture.

A Python wrapper for the Live2D Native SDK that allows direct loading and rendering of Live2D models using OpenGL without needing a web engine.

Mamba YOLO is an object detection baseline that replaces traditional architectures with State Space Models to provide an efficient alternative for real-time detection.

A MATLAB toolbox for the advanced analysis of MEG, EEG, and iEEG data, supporting multiple hardware formats and source reconstruction.

SimBA is a GUI-based toolkit that lets researchers train supervised machine-learning classifiers to automatically detect and quantify animal behaviors from pose-estimation video data, without needing programming skills. It turns raw tracking data into validated behavioral classifications and rich downstream analyses for behavioral neuroscience.

A command-line tool for running AI-based weather forecasting models, providing a unified interface for data retrieval and model execution.

An extension of Open3D that provides tools, pretrained models, and pipelines for 3D machine learning tasks like semantic segmentation and object detection.

A C++ library for high-dimensional medical image registration and segmentation, used to analyze brain structure and function across species and organ systems.

An Android SDK for facial recognition and 3D passive liveness detection to prevent spoofing in security and fintech applications.

A multi-view, multi-source benchmark and baseline for drone-based geo-localization, enabling the matching of drone, satellite, and street-view images to locate buildings.

Supervisely is a web‑based computer‑vision platform that combines data labeling, model training, inference and collaboration tools. It offers a Python SDK and REST API for automation, and an app ecosystem where developers can create head‑less scripts, interactive UI tools, or labeling‑tool extensions—all deployable with a single click.

Custom ComfyUI nodes that integrate Depth Anything V3 for high-quality depth estimation, 3D point cloud reconstruction, and consistent video depth mapping.

An automated document processor that uses local Vision AI via Ollama to analyze scanned PDFs and automatically rename them with descriptive filenames.

A Python toolbox for facial expression research that detects faces and extracts emotional expressions, facial muscle movements, and landmarks from images and videos.

ZUNA1.1 is an open foundation model for EEG that denoises, reconstructs missing channels, and upsamples sparse electrode layouts using 3D scalp coordinates.

PEAR is a real-time framework for expressive 3D human mesh recovery that can predict human mesh parameters at 100 FPS from images or video.

A comprehensive benchmark and modular codebase for image manipulation detection and localization, providing standardized components and SOTA model implementations.

Count Anything is a research model that counts objects in images based on a natural‑language query. It works across six domains (scenes, satellite, medical, etc.) by combining a sparse region counter and a dense pixel counter, merging their results with a parameter‑free fusion step. The repo provides a pretrained checkpoint, training/evaluation scripts, and instructions for preparing the large CLOC dataset.

EdgeCrafter provides compact Vision Transformers (ViTs) optimized for edge devices, enabling high-performance object detection, instance segmentation, and pose estimation with low latency.

A specialized implementation of YOLOv3 designed to train and run object detection on the xView satellite imagery dataset for remote sensing applications.

A library for chest X-ray datasets and models, providing pre-trained models and a uniform interface for working with multiple public chest X-ray datasets.

A real-time video magnification tool that amplifies subtle motion and color changes using Eulerian video magnification techniques.

A local-first data curation and annotation tool for computer vision datasets that uses embeddings to help users efficiently manage and label image and video data.

An ultra-lightweight, anchor-free real-time object detection algorithm optimized for high-speed inference on ARM CPUs and embedded devices.

A media analytics framework based on GStreamer and OpenVINO that enables hardware-accelerated video and audio intelligence pipelines on Intel CPU, GPU, and NPU.

A collection of Unity samples for Meta Quest 3/3S that enables mixed reality experiences to detect objects, track QR codes, and use multimodal AI to understand the surroundings.

A deep learning framework for point cloud analysis that provides a high-level API and a library of state-of-the-art models for 3D classification, segmentation, and detection.

A library implementing Wavelet Convolutions to provide CNNs with large receptive fields, featuring optimized backends for CUDA, Metal, and Triton.

A Three.js-based Web renderer for 3D Gaussian Splatting that enables high-performance streaming and adaptive LOD for large-scale 3D scenes.

A GPU-native Structure from Motion (SfM) pipeline that accelerates the process of reconstructing 3D structures from 2D images, including integrated support for 3D Gaussian Splatting.

An interactive machine learning toolkit for segmenting, classifying, tracking, and counting cells and other experimental image data.