TESSERA is an open geospatial foundation model that converts cloud-corrupted satellite time series into compact 128-dimensional embeddings for global Earth representation and analysis.

A comprehensive PyTorch library implementing the original Vision Transformer (ViT) and dozens of its architectural variants for image classification.

An open-source reproduction of AlphaFold3 for predicting the 3D structures of proteins, RNA, DNA, and small molecules.

A PyTorch-based open-source framework for deep learning in healthcare imaging that provides standardized workflows and domain-specific tools for medical data.

A comprehensive benchmark for evaluating document parsing in real-world scenarios, featuring rich annotations for layout detection, OCR, table, and formula recognition.

An MIT-licensed computer vision library that provides a single API for detection, segmentation, pose, depth, OCR, and other vision tasks, including training and export tools.

A spatial AI tool that estimates camera poses, intrinsics, and dense depth maps from raw videos, including wide-angle and 360-degree panorama footage.

A high-speed GPU document parser that converts images and PDFs into structured Markdown, including tables and formulas, using C++, CUDA, and TensorRT.

A training-free framework that converts SAM3 into a real-time multi-class open-vocabulary detector using TensorRT optimization and distilled backbones.

A multi-modal biometric login system for Linux that enables face and fingerprint authentication with AI-powered anti-spoofing and a GUI manager.

A tool that converts static images or sketches into smooth drawing animations by transforming them into SVGs and rendering them with Manim.

Pre-built Python bindings for OpenCV that allow users to install the computer vision library via pip without needing to manual compilation.

A PyTorch library providing popular datasets, model architectures, and image transformations for computer vision.

A PyTorch-powered OCR library that provides a seamless pipeline for text detection and recognition in PDFs and images, including layout and table analysis.

ZipDepth is a 6 M‑parameter, zero‑shot monocular depth model that runs at >1 k FPS on GPUs and can be exported to mobile runtimes. It combines RepVGG‑style re‑parameterizable convolutions, strip‑pooling attention, and a lightweight FPN decoder. The repo provides ready‑to‑run inference scripts, ONNX/TorchScript export utilities, benchmarks, and full training pipelines (knowledge‑distilled from Depth Anything V2).

A semi-supervised 3D tooth segmentation framework that enhances nnU-Net with axial attention and a positional correction module to improve accuracy using limited labeled data.

A research-oriented, differentiable rendering system for forward and inverse light transport simulation with deep Python integration.

SAHI (Slicing‑Aided Hyper Inference) is an open‑source Python library that enables sliced inference for object detection and instance segmentation on very large images or video. It works with most popular detectors (YOLO, MMDetection, Detectron2, HuggingFace, TorchVision, etc.), provides a CLI and Python API, integrates with FiftyOne for visualisation, and includes utilities for COCO dataset handling and evaluation.

A cross-platform desktop application for AI-assisted video masking, segmentation, and object removal using models like SAM2 and MatAnyone.

OpenSplat is a C++ implementation of 3‑D Gaussian splatting that converts COLMAP/OpenSfM/ODX/nerfstudio data into compact Gaussian‑based scene files. It supports CUDA, ROCm (HIP), Apple Metal, and CPU‑only builds, offers Docker images, and provides a simple CLI for training, resuming, masking, and exporting to .ply/.splat/.spz/.rad formats.

A visual fiducial system for robotics that detects unique markers in images to provide precise identification and 3D pose estimation.

A facial authentication system for Linux that provides on-device face recognition and PAM integration for secure, passwordless login and sudo access.

A Doom-based AI research platform for developing and testing bots that play the game using only visual information, primarily for reinforcement learning research.

An inference engine and deployment platform that enables users to run computer vision models and complex visual workflows on any hardware, from edge devices to the cloud.

A PyTorch library for explainable AI in computer vision that provides a wide range of pixel attribution methods to visualize and diagnose model predictions.

A lightweight version of SAM3 that uses knowledge distillation to compress vision and text encoders, reducing model size by up to 90% for efficient segmentation.

rtmlib is a lightweight Python library for human and animal pose estimation that wraps RTMPose and ViTPose models. It avoids heavy OpenMMLab dependencies, requiring only numpy, OpenCV and ONNX Runtime (with optional GPU/accelerator back‑ends). The package provides high‑level solution classes (Wholebody, Body, Hand, Animal, Custom, Wholebody3d) that combine a detector (YOLOX, RFDETR, RTMDet) and a pose estimator, plus utilities for drawing skeletons. Models are auto‑downloaded from OpenMMLab or a HuggingFace mirror. Install via pip or from source, and run a Gradio WebUI or use the Python API for single‑image, video, or webcam inference.

A ComfyUI custom node suite for advanced image background removal and precise object segmentation using a wide array of AI models like RMBG-2.0 and SAM2.

LitePT is a lightweight, high-performance 3D point cloud architecture that reduces parameter count and memory footprint while maintaining state-of-the-art accuracy for 3D vision tasks.

A deep learning tool for recognizing and swapping faces in pictures and videos through an extract-train-convert pipeline.

An open-source OMR checking software that uses computer vision to accurately read and evaluate scanned OMR sheets or mobile photos, exporting results to CSV.

A high-performance camera library for React Native that enables professional photo/video capture and real-time AI frame processing.

A highly optimized, parallelized C++ library for fine point cloud registration (ICP, GICP, VGICP) designed for high-speed 3D alignment.

A tool that converts noisy, high-resolution pixel-art-style images and animations into clean, true-resolution pixel assets by recovering the underlying grid.

A real-time dense feed-forward scene reconstruction system for 3D mapping and localization, featuring optional open-set 3D object detection.

A self-hosted, local-only NVR and AI computer vision software for home and office monitoring with object and face recognition.

An OCR engine that extracts either raw text or structured JSON data from receipt images using Tesseract and LLMs.

MonkeyOCR is a document parsing model that uses a Structure-Recognition-Relation triplet paradigm to convert PDFs and images into structured Markdown, supporting English and Chinese.

A lightweight, end-to-end OCR vision-language model that unifies document parsing and text extraction with speculative decoding for faster inference.

A desktop application for AI-powered face swapping and enhancement across images, videos, and live webcam feeds, featuring professional editing tools and GPU acceleration.

Nilearn is a Python library for the analysis of brain volumes and surfaces using statistical and machine learning tools, leveraging scikit-learn for multivariate statistics.

An open-source toolkit for general OCR, providing lightweight models for unified text, formula, and table recognition and document parsing.

SOMA‑X is a Python library that offers a unified, differentiable representation of parametric human bodies and hands, supporting multiple identity models (MHR, SMPL‑X, MANO, etc.) and providing fast skinning via NVIDIA Warp. It includes `SOMALayer` and `SOMAHandLayer` for full‑body and hand meshes at several levels of detail, plus tools for pose inversion, rig control, and data I/O, making it useful for animation, pose‑estimation fitting, and synthetic data generation.

A Windows facial recognition unlock tool that uses OpenCV and a custom Credential Provider to enable face-unlock capabilities on devices without native Windows Hello hardware.

A standalone C++ inference engine for SAM-3D-Body that regresses 3D human body pose, shape, and camera parameters from 2D images without Python dependencies.

A collection of computer vision tools and datasets for sports analytics, focusing on challenges like ball tracking, player re-identification, and jersey number OCR.

An open-source AI camera platform that enables local deployment of VLM scene analysis and object detection skills with autonomous, hardware-aware installation.

An end-to-end motion capture system that converts monocular videos into 3D joint rotations for arbitrary skeletons, including animals and custom rigs.