A framework and dataset for disentangling task transfer learning in computer vision, providing a pretrained task bank and tools to analyze task affinities.

A computer vision project that enhances shuttlecock tracking in badminton videos using trajectory prediction with background estimation and an inpainting-based rectification module to handle occlusions.

A real-time visual target detection and tracking system based on YOLOv5, optimized for low-latency screen capture and GPU inference in gaming scenarios.

A command-line and GUI application that automatically detects motion events in video files and saves each event as a separate clip.

A Telegram bot that identifies anime titles, episodes, and timestamps from screenshots or videos using the trace.moe service.

An open-source eye tracking platform that provides the software infrastructure for capturing, playing back, and analyzing eye-tracking data.

A high-performance C/C++ image processing and machine learning library that uses SIMD CPU extensions to accelerate algorithms across x86, ARM, and Hexagon architectures.

ELSED is a high-speed line segment detector designed for resource-limited devices like drones and smartphones.

An on-device face recognition and liveness detection SDK for Android that enables private, offline biometric identity verification and attribute analysis.

A Unity plugin that integrates ZED cameras' depth sensing, spatial mapping, and object detection capabilities into the Unity engine for AR/MR development.

A natural language image search tool that allows users to find specific images in local folders using text or image queries powered by OpenAI's CLIP.

A multi-image viewer designed for efficient comparison, filtering, and stitching of large image datasets, featuring parallel zooming and automated figure generation.

GeoCLIP is a CLIP-inspired model that aligns images with geographical locations to enable high-accuracy worldwide image geo-localization and GPS-to-vector embeddings.

A Python toolbox for evaluating grayscale and binary image segmentation models, providing comprehensive metrics and automated curve plotting.

UGround is an open‑source visual‑language model (2 B/7 B/72 B) fine‑tuned to locate UI elements in screenshots from a textual description. The repo ships pretrained weights, a >1 M‑image GUI grounding dataset, evaluation scripts for four benchmarks, and a Hugging Face demo. Inference runs via vLLM with a simple prompt that returns (x, y) coordinates. The 72 B model achieves state‑of‑the‑art scores on the ScreenSpot benchmark and is described in an ICLR 2025 oral paper.

A fast, lightweight Flutter plugin for scanning barcodes and QR codes with the device camera, supporting Android, iOS, macOS, and web with real-time detection and customizable camera behavior.

A Python library for cloud-native Synthetic Aperture Radar (SAR) processing that provides geometric and radiometric terrain correction for Sentinel-1 satellite data.

A Python implementation of the RANSAC method for fitting primitive geometric shapes to 3D point clouds, useful for 3D reconstruction and SLAM.

A cross-platform C++/Python development toolkit for connecting to, configuring, and visualizing data from Ouster Lidar sensors.

A repository of extra data and resources that supplement the core OpenCV computer vision library.

A research framework for developing and benchmarking deep graph matching algorithms to find node-to-node correspondences between graphs.

A minimalistic and portable C-based computer vision library providing state-of-the-art algorithms for face, object, and text detection.

A comprehensive image recognition and classification toolkit providing ultra-lightweight models and industrial-grade backbones for high-performance vision applications.

A PyTorch-based supervised semantic segmentation toolbox providing a unified framework and extensive model zoo for training and testing segmentation algorithms.

A standardized evaluation framework for CLIP-like models to measure performance on zero-shot classification, retrieval, captioning, and linear probing across diverse datasets.

A single-stage 3D scene reconstruction tool that creates 3D point clouds and camera poses from sparse RGB views in about 2 seconds without requiring pre-known camera poses.

A Python package for detecting and segmenting grains in images using a hybrid U-Net and SAM 2.1 approach, designed for geomorphology and sedimentary geology research.

A facial expression recognition system using a Residual Masking Network to detect human emotions from images and live video feeds.

A PyTorch implementation for jointly reconstructing 3D topology, materials, and lighting from multi-view images using Monte Carlo rendering and denoising.

A neural networks toolbox for medical image analysis that provides specialized tensor operations, prebuilt architectures, and plotting tools for spatial data.

A JavaScript library for performing OCR and text extraction from images and PDFs, capable of creating searchable PDFs with invisible text layers.

A PyTorch-based tool for detecting anime faces and estimating 28 facial landmark points using pretrained Faster R-CNN, YOLOv3, and HRNetV2 models.

A cross-platform computer vision framework for tracking fiducial markers and multi-touch fingers to enable the creation of tangible user interfaces.

The official Python package for Roboflow, enabling developers to interact with models, datasets, and projects to build and deploy computer vision models programmatically.

A real-time computer vision library written in Java that provides tools for low-level image processing, camera calibration, and feature tracking.

A TensorFlow-based handwritten text recognition system that converts images of single words or text lines into digital text using CNN and LSTM layers.

A browser-based web application for recognizing text from images, proofreading OCR data with high precision, and creating fully digitized, ebook-style documents.

A NASA-developed C++ library for general-purpose image processing and computer vision, providing tools for camera models, cartographic projections, and mosaic compositing.

A PyTorch library implementing various graph neural networks for weather forecasting and data assimilation, including models like GenCast and Aurora.

A modular C++ library with Python bindings that implements the Iterative Closest Point (ICP) algorithm for aligning 3D point clouds in robotics and computer vision.

A GPU-accelerated library for processing triangle meshes, featuring integrated matrix infrastructure and automatic differentiation for geometry processing tasks.

A collection of minimal solvers and robust estimators for camera pose estimation, supporting various correspondences and camera models with minimal dependencies.

A ComfyUI integration for Meta's SAM3 that enables open-vocabulary image and video segmentation using natural language text prompts.

A family of open-source, cost-effective vision encoders for multimodal learning that optimizes training efficiency and performance across understanding and generation tasks.

A hardware documentation and design-resource hub for the reCamera series of AI-powered vision modules with integrated NPUs for edge AI.

CellProfiler is an open-source software that enables biologists to automatically and quantitatively measure phenotypes from thousands of images without requiring programming or computer vision expertise.

A Python library for building AI-powered image search systems supporting text, image, and hybrid search using multimodal embeddings and vector indexing.

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