vincentqyw/image-matching-webui

Image Matching WebUI Matching Keypoints between two images

Description

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:

https://github.com/Vincentqyw/image-matching-webui/assets/18531182/263534692-c3484d1b-cc00-4fdc-9b31-e5b7af07ecd9

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

How to use

HuggingFace / Lightning AI

Just try it on

or deploy it locally following the instructions below.

Requirements

• Python 3.10+

Install from pip [NEW]

Update: now support install from pip, just run:

pip install imcui

Install from source

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

Deploy to Railway

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

python -m imcui.api.server

Run demo

# Using the package CLI (recommended)
imcui

# Or using the direct script
python app.py

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

Command Line Interface

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

Basic Usage

Command Line Options

Add your own feature / matcher

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.

For a detailed step-by-step guide, see CLAUDE.md and the integrate-matcher skill at .claude/skills/integrate-matcher/SKILL.md.

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)

Upload models

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

Contributions welcome!

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:

• [x] support pip install command
• [x] add CPU CI
• [x] add webcam support
• [x] add line feature matching algorithms
• [x] example to add a new feature extractor / matcher
• [x] ransac to filter outliers
• [ ] add rotation images options before matching
• [ ] support export matches to colmap (#issue 6)
• [x] add config file to set default parameters
• [x] 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:

To format code before committing, run:

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

Contributors

Resources

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

Acknowledgement

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