gmberton/vismatch

Wrapper of 50+ image matching models with a unified interface

What it solves

VisMatch provides a unified API to easily access and compare over 50 different image matching models. Instead of implementing each model's specific code and handling separate weight downloads, users can test various matching techniques (dense, semi-dense, and sparse) through a single interface.

How it works

The library wraps numerous existing image matching models and provides a consistent Python API and Command Line Interface (CLI). It automatically handles the downloading of model weights from HuggingFace and allows users to perform two primary tasks:

  1. Matching: Finding corresponding points between two images (e.g., outdoor scenes, satellite imagery, or paintings).
  2. Extraction: Extracting keypoints and their associated descriptors from a single image.

Who it’s for

It is designed for researchers and developers working in computer vision, specifically those needing to perform image registration, coregistration, or localization across diverse scenes.

Highlights

  • Extensive Model Library: Supports 50+ models categorized into dense, semi-dense, and sparse matchers.
  • Unified Interface: A single get_matcher function allows switching between models with one line of code.
  • Automated Weights: Model weights are automatically downloaded, removing manual setup overhead.
  • Flexible Input: Supports images, folders of images, or files containing image paths via the CLI.
  • Built-in Visualization: Includes utility functions to plot matches and keypoints.

Related

  • Project
    zju3dv/MatchAnything

    MatchAnything is a research project that trains a single neural network to find correspondences between images from any visual modality (e.g., RGB, infrared, sketches). Pre‑trained weights are hosted on Hugging Face, and an online demo lets users try cross‑modality matching instantly. The approach aims to replace many specialized matching pipelines with one universal model, useful for robotics, remote sensing, medical imaging, and AR.

  • Project
    yakhyo/uniface

    UniFace is a Python library that unifies 15 face‑analysis tasks—detection, landmarks, 3‑D mesh, parsing, matting, gaze, head pose, demographics, emotion, quality, anti‑spoofing, recognition, anonymisation, and FAISS‑based similarity—into a single, easy‑to‑install package (CPU, Apple Silicon, or CUDA). It provides a consistent API, auto‑downloads verified model weights, and includes extensive docs, notebooks, and a community Discord.

  • Project
    LibreYOLO/libreyolo

    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.

  • Dispatch
    Image Similarity with Hugging Face Datasets and Transformers

    Hugging Face demonstrates how to build an image similarity system using the Transformers and Datasets libraries by computing dense vector embeddings and measuring cosine similarity.

  • Project
    tomas-gajarsky/facetorch

    A Python library for facial detection and analysis that curates and optimizes open-source deep learning models for tasks like emotion recognition and deepfake detection.