Computer Vision

Onnx Text Recognition (OnnxTR) OCR plugin for docling

An open source framework for deep learning on satellite and aerial imagery

OpenMMLab Model Pretraining Toolbox and Benchmark

differential geometric computer vision for deep learning

Pymba is a Python wrapper for Allied Vision's Vimba C API.

The main rastervision package for configuring, defining, and running pipelines

A rastervision plugin that adds geospatial machine learning pipelines

A rastervision plugin that adds PyTorch training pipelines

A rastervision plugin that adds PyTorch backends for rastervision.core pipelines

A rastervision plugin that adds an AWS S3 file system

A rastervision plugin that adds an AWS Batch pipeline runner

OpenMMLab Computer Vision Foundation

Fast symbolic computation, code generation, and nonlinear optimization for robotics

OpenMMLab Model Deployment

A super-fast Python implementation of seam carving algorithm for intelligent image resizing.

Savant Rust core functions library

Computer Vision Helping Library

Skeletonize densely labeled image volumes.

Extracting image features from state-of-the-art neural networks for Computer Vision made easy

DataGradients

AI2-THOR: A Near Photo-Realistic Interactable Framework for Embodied AI Agents

A lightweight Computer Vision library for high-performance AI research - Modern Computer Vision on the Fly.

AI-Powered Command-Line Photo Search Tool

equirectangular image processing with python using minimum dependencies

Conversions between kornia and other computer vision libraries formats

cuCIM - an extensible toolkit designed to provide GPU accelerated I/O, computer vision & image processing primitives for N-Dimensional images with a focus on biomedical imaging.

Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv

Easily computing clip embeddings and building a clip retrieval system with them

quick_ml : Computer Vision For Everyone. Official Website -> www.antoreepjana.wixsite.com/quick-ml. Making Deep Learning through TPUs accessible to everyone. Lesser Code, faster computation, better modelling.

🔥LIT: The Learning Interpretability Tool

Industry-strength computer Vision extensions for Keras.

Viewing and rendering of sequences of 3D data.

Transformer Library for 3D Mesh Processing

Fast, memory-efficient image tiling and reconstruction for deep learning and scientific computing

A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

Top-level package for skellycam.

A computer vision pipeline for the semantic exploration of maps/images at scale

[DEPRECATED] An inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application

Vid2Info is an easy-to-use Computer Vision pipeline that implements Detection, Tracking and, optionally, Segmentation.

Python package for Grayness Index

CUDA-accelerated Computer Vision algorithms

Automation with Computer Vision for Python

PlantCV: Plant phenotyping with computer vision

Natural Robustness Toolkit (NRTK) is a platform for generating validated, sensor-specific perturbations and transformations used to evaluate the robustness of computer vision models.

Glasses classification, detection, and segmentation.

MCP服务器：火山引擎图像编辑工具，提供显著性分割、背景移除等图像处理功能

doc2text drastically improves the extraction of text from images by fixing resolution, text area (crop), and skew.

Tensorflow keras computer vision attention models. Alias kecam. https://github.com/leondgarse/keras_cv_attention_models

Fast, flexible, and advanced augmentation library for deep learning, computer vision, and medical imaging. Albumentations offers a wide range of transformations for both 2D (images, masks, bboxes, keypoints) and 3D (volumes, volumetric masks, keypoints) data, with optimized performance and seamless integration into ML workflows.

A barcode reader extension module using zxing-cpp and pyo3