Image Matching WebUI (IMCUI) efficiently matches image pairs using multiple famous image matching algorithms. The tool features a Graphical User Interface (GUI) designed using gradio. You can effortlessly select two images and a matching algorithm and obtain a precise matching result. Note: the images source can be either local images or webcam images.

Try it on

Here is a demo of the tool:

The tool currently supports various popular image matching algorithms, namely:

Just try it on

or deploy it locally following the instructions below.

• Python 3.9+

Update: now support install from pip, just run:

pip install imcui

git clone --recursive https://github.com/Vincentqyw/image-matching-webui.git
cd image-matching-webui
conda env create -f environment.yaml
conda activate imcui
pip install -e .

or using docker:

docker pull vincentqin/image-matching-webui:latest

# Start the WebUI service
docker-compose up webui

# Or run in the background
docker-compose up -d webui

# Build and start the WebUI service
docker-compose up --build webui

# Check the status of the WebUI service
docker-compose ps webui

# View logs for the WebUI service
docker-compose logs webui
docker-compose logs -f webui  # Follow logs in real time

# Stop the WebUI service
docker-compose stop webui

# Restart the WebUI service
docker-compose restart webui

# Remove the WebUI service container
docker-compose rm webui

# Remove all containers
docker-compose down

Deploy to Railway, setting up a Custom Start Command in Deploy section:

python -m imcui.api.server

# Using the package CLI (recommended)
imcui

# Or using the direct script
python app.py

then open http://localhost:7860 in your browser.

The imcui package provides a powerful command-line interface with various options:

# Install the package
pip install imcui

# Run with default settings
imcui

# Run with verbose output
imcui --verbose

# Run on a specific port
imcui -p 7860

# Run on a specific host
imcui -s 127.0.0.1

# Help
imcui --help

I provide an example to add local feature in imcui/hloc/extractors/example.py. Then add feature settings in confs in file imcui/hloc/extract_features.py. Last step is adding some settings to matcher_zoo in your configuration file.

Configuration file locations (in priority order):

1. Custom config file specified with --config parameter
2. config.yaml in current directory
3. config/config.yaml in current directory
4. Package default config (imcui/config/app.yaml)

IMCUI hosts all models on Huggingface. You can upload your model to Huggingface and add it to the Realcat/imcui_checkpoints repository.

External contributions are very much welcome. Please follow the PEP8 style guidelines using a linter like flake8. This is a non-exhaustive list of features that might be valuable additions:

• support pip install command
• add CPU CI
• add webcam support
• add line feature matching algorithms
• example to add a new feature extractor / matcher
• ransac to filter outliers
• add rotation images options before matching
• support export matches to colmap (#issue 6)
• add config file to set default parameters
• dynamically load models and reduce GPU overload

Adding local features / matchers as submodules is very easy. For example, to add the GlueStick:

git submodule add https://github.com/cvg/GlueStick.git imcui/third_party/GlueStick

If remote submodule repositories are updated, don't forget to pull submodules with:

git submodule update --init --recursive  # init and download
git submodule update --remote  # update

If you only want to update one submodule, use git submodule update --remote imcui/third_party/GlueStick.

To remove a submodule, follow these steps:

git submodule deinit -f imcui/third_party/GlueStick
git rm -f imcui/third_party/GlueStick
rm -rf .git/modules/imcui/third_party/GlueStick
git add .gitmodules && \
git commit -m "Remove submodule imcui/third_party/dust3r"

To format code before committing, run:

pre-commit run -a  # Auto-checks and fixes

• Image Matching: Local Features & Beyond
• Long-term Visual Localization

This code is built based on Hierarchical-Localization. We express our gratitude to the authors for their valuable source code.