The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

🦀 Low-level 3D Computer Vision library in Rust

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Industry leading face manipulation platform

💻 Get seamless remote access to any Linux device. Centralized SSH for the edge and cloud computing

libusb driver for the g13

Logitech G13 driver and configuration tool for Linux Systems

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

PyTorch media decoding and encoding

The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment

High-performance, optimized pre-trained template AI application pipelines for systems using Hailo devices

This package allows to create and manage Single Unique Processes

We write your reusable computer vision tools. 💜

An open source light-weight and high performance inference framework for Hailo devices

computer vision and sports

OpenVPN road warrior installer for Ubuntu, Debian, AlmaLinux, Rocky Linux, CentOS and Fedora

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

Tesseract Open Source OCR Engine (main repository)

Multi-Player Tracking Dataset for Ice-Hockey

Recognition of pressed gamepad buttons

OCR, layout analysis, reading order, table recognition in 90+ languages

Python 3 implementation of the Hungarian Algorithm

Pythonic bindings for FFmpeg's libraries.

SoccerNet@CVPR | 1st place solution for Ball Action Spotting Challenge 2023

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.