update: dev

.clang-format

@@ -1,40 +0,0 @@
-BasedOnStyle: Chromium
-IncludeBlocks: Preserve
-IncludeCategories:
-  - Regex: '^<.*>'
-    Priority: 1
-  - Regex: '^".*"'
-    Priority: 2
-SortIncludes: true
-Language: Cpp
-AccessModifierOffset: 2
-AlignAfterOpenBracket: true
-AlignConsecutiveAssignments: false
-AlignConsecutiveDeclarations: false
-AlignEscapedNewlines: Right
-AlignOperands: true
-AlignTrailingComments: false
-AllowAllParametersOfDeclarationOnNextLine: true
-AllowShortBlocksOnASingleLine: false
-AllowShortCaseLabelsOnASingleLine: true
-AllowShortFunctionsOnASingleLine: None
-AllowShortIfStatementsOnASingleLine: true
-AllowShortLoopsOnASingleLine: true
-AlwaysBreakAfterReturnType: None
-AlwaysBreakBeforeMultilineStrings: true
-AlwaysBreakTemplateDeclarations: false
-BinPackArguments: false
-BinPackParameters: false
-BreakBeforeBraces: Attach
-BreakBeforeInheritanceComma: false
-BreakBeforeTernaryOperators: true
-BreakStringLiterals: false
-ColumnLimit: 88
-CompactNamespaces: false
-ConstructorInitializerAllOnOneLineOrOnePerLine: true
-ConstructorInitializerIndentWidth: 4
-ContinuationIndentWidth: 4
-IndentCaseLabels: true
-IndentWidth: 4
-TabWidth: 4
-UseTab: Never

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 80
+extend-ignore = E203,E501,E402
+exclude = .git,__pycache__,build,.venv/,third_party

.github/workflows/ci.yml

@@ -11,7 +11,6 @@ on:
 jobs:
   build:
     runs-on: ubuntu-latest
-    # runs-on: self-hosted
 
     steps:
     - name: Checkout code
@@ -29,9 +28,5 @@ jobs:
         pip install -r requirements.txt
         sudo apt-get update && sudo apt-get install ffmpeg libsm6 libxext6 -y
 
-    - name: Build and install
-      run: pip install .
-
     - name: Run tests
-      # run: python -m pytest
-      run: python tests/test_basic.py
+      run: python test_app_cli.py

.github/workflows/format.yml

@@ -1,23 +1,24 @@
-# This is a format job. Pre-commit has a first-party GitHub action, so we use
-# that: https://github.com/pre-commit/action
-
-name: Format
-
+name: Format and Lint Checks
 on:
-  workflow_dispatch:
-  pull_request:
   push:
     branches:
-    - main
-
+      - main
+    paths:
+      - '*.py'
+  pull_request:
+    types: [ assigned, opened, synchronize, reopened ]
 jobs:
-  pre-commit:
-    name: Format
+  check:
+    name: Format and Lint Checks
     runs-on: ubuntu-latest
-    # runs-on: self-hosted
     steps:
-    - uses: actions/checkout@v4
-    - uses: actions/setup-python@v5
-      with:
-        python-version: "3.x"
-    - uses: pre-commit/action@v3.0.1
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+          cache: 'pip'
+      - run: python -m pip install --upgrade pip
+      - run: python -m pip install .[dev]
+      - run: python -m flake8 ui/*.py hloc/*.py hloc/matchers/*.py hloc/extractors/*.py 
+      - run: python -m isort ui/*.py hloc/*.py hloc/matchers/*.py hloc/extractors/*.py --check-only --diff
+      - run: python -m black ui/*.py hloc/*.py hloc/matchers/*.py hloc/extractors/*.py --check --diff

.github/workflows/pip.yml

@@ -1,62 +0,0 @@
-name: Pip
-on:
-  workflow_dispatch:
-  pull_request:
-  push:
-    branches:
-      - main
-
-jobs:
-  build:
-    strategy:
-      fail-fast: false
-      matrix:
-        platform: [ubuntu-latest]
-        python-version: ["3.9", "3.10"]
-
-    runs-on: ${{ matrix.platform }}
-    # runs-on: self-hosted
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        submodules: recursive
-
-    - uses: actions/setup-python@v5
-      with:
-        python-version: ${{ matrix.python-version }}
-
-    - name: Upgrade setuptools and wheel
-      run: |
-        pip install --upgrade setuptools wheel
-
-    - name: Install dependencies on Ubuntu
-      if: runner.os == 'Linux'
-      run: |
-        sudo apt-get update
-        sudo apt-get install libopencv-dev -y
-
-    - name: Install dependencies on macOS
-      if: runner.os == 'macOS'
-      run: |
-        brew update
-        brew install opencv
-
-    - name: Install dependencies on Windows
-      if: runner.os == 'Windows'
-      run: |
-        choco install opencv -y
-
-    - name: Add requirements
-      run: python -m pip install --upgrade wheel setuptools
-
-    - name: Install Python dependencies
-      run: |
-        pip install pytest
-        pip install -r requirements.txt
-        sudo apt-get update && sudo apt-get install ffmpeg libsm6 libxext6 -y
-
-    - name: Build and install
-      run: pip install .
-
-    - name: Test
-      run: python -m pytest

.github/workflows/release-drafter.yml

@@ -0,0 +1,16 @@
+name: Release Drafter
+
+on:
+  push:
+    # branches to consider in the event; optional, defaults to all
+    branches:
+      - master
+
+jobs:
+  update_release_draft:
+    runs-on: ubuntu-latest
+    steps:
+      # Drafts your next Release notes as Pull Requests are merged into "master"
+      - uses: release-drafter/release-drafter@v5.23.0
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/release.yml

@@ -1,95 +0,0 @@
-name: PyPI Release
-on:
-  release:
-    types: [published]
-
-jobs:
-  build:
-    strategy:
-      fail-fast: false
-      matrix:
-        platform: [ubuntu-latest]
-        python-version: ["3.9", "3.10", "3.11"]
-
-    runs-on: ${{ matrix.platform }}
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        submodules: recursive
-
-    - uses: actions/setup-python@v5
-      with:
-        python-version: ${{ matrix.python-version }}
-
-    - name: Upgrade setuptools and wheel
-      run: |
-        pip install --upgrade setuptools wheel
-
-    - name: Install dependencies on Ubuntu
-      if: runner.os == 'Linux'
-      run: |
-        sudo apt-get update
-        sudo apt-get install libopencv-dev -y
-
-    - name: Install dependencies on macOS
-      if: runner.os == 'macOS'
-      run: |
-        brew update
-        brew install opencv
-
-    - name: Install dependencies on Windows
-      if: runner.os == 'Windows'
-      run: |
-        choco install opencv -y
-
-    - name: Add requirements
-      run: python -m pip install --upgrade setuptools wheel build
-
-    - name: Install Python dependencies
-      run: |
-        pip install pytest
-        pip install -r requirements.txt
-        sudo apt-get update && sudo apt-get install ffmpeg libsm6 libxext6 -y
-
-    - name: Build source distribution
-      run: |
-        python -m build --outdir dist/
-        ls -lh dist/
-
-    - name: Upload to GitHub Release
-      if: matrix.python-version == '3.10' && github.event_name == 'release'
-      uses: softprops/action-gh-release@v2
-      with:
-        files: dist/*.whl
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-    - name: Archive wheels
-      if: matrix.python-version == '3.10' && github.event_name == 'release'
-      uses: actions/upload-artifact@v4
-      with:
-        name: dist
-        path: dist/*.whl
-
-
-  pypi-publish:
-    name: upload release to PyPI
-    needs: build
-    runs-on: ubuntu-latest
-    environment: pypi
-    permissions:
-      # IMPORTANT: this permission is mandatory for Trusted Publishing
-      id-token: write
-    steps:
-      # retrieve your distributions here
-      - name: Download artifacts
-        uses: actions/download-artifact@v4
-        with:
-          name: dist
-          path: dist
-
-      - name: List dist directory
-        run: ls -lh dist/
-
-      - name: Publish package distributions to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1

.gitignore

@@ -1,4 +1,5 @@
 build/
+# lib
 bin/
 cmake_modules/
 cmake-build-debug/
@@ -25,9 +26,3 @@ gen_example.py
 datasets/lines/terrace0.JPG
 datasets/lines/terrace1.JPG
 datasets/South-Building*
-*.pkl
-oryx-build-commands.txt
-.ruff_cache*
-dist
-tmp
-backup*

.pre-commit-config.yaml

@@ -1,88 +0,0 @@
-# To use:
-#
-#     pre-commit run -a
-#
-# Or:
-#
-#     pre-commit run --all-files
-#
-# Or:
-#
-#     pre-commit install  # (runs every time you commit in git)
-#
-# To update this file:
-#
-#     pre-commit autoupdate
-#
-# See https://github.com/pre-commit/pre-commit
-
-ci:
-  autoupdate_commit_msg: "chore: update pre-commit hooks"
-  autofix_commit_msg: "style: pre-commit fixes"
-
-repos:
-# Standard hooks
-- repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v5.0.0
-  hooks:
-  - id: check-added-large-files
-    exclude: ^imcui/third_party/
-  - id: check-case-conflict
-    exclude: ^imcui/third_party/
-  - id: check-merge-conflict
-    exclude: ^imcui/third_party/
-  - id: check-symlinks
-    exclude: ^imcui/third_party/
-  - id: check-yaml
-    exclude: ^imcui/third_party/
-  - id: debug-statements
-    exclude: ^imcui/third_party/
-  - id: end-of-file-fixer
-    exclude: ^imcui/third_party/
-  - id: mixed-line-ending
-    exclude: ^imcui/third_party/
-  - id: requirements-txt-fixer
-    exclude: ^imcui/third_party/
-  - id: trailing-whitespace
-    exclude: ^imcui/third_party/
-
-- repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: "v0.8.4"
-  hooks:
-    - id: ruff
-      args: ["--fix", "--show-fixes", "--extend-ignore=E402"]
-    - id: ruff-format
-      exclude: ^(docs|imcui/third_party/)
-
-# Checking static types
-- repo: https://github.com/pre-commit/mirrors-mypy
-  rev: "v1.14.0"
-  hooks:
-    - id: mypy
-      files: "setup.py"
-      args: []
-      additional_dependencies: [types-setuptools]
-      exclude: ^imcui/third_party/
-# Changes tabs to spaces
-- repo: https://github.com/Lucas-C/pre-commit-hooks
-  rev: v1.5.5
-  hooks:
-  - id: remove-tabs
-    exclude: ^(docs|imcui/third_party/)
-
-# CMake formatting
-- repo: https://github.com/cheshirekow/cmake-format-precommit
-  rev: v0.6.13
-  hooks:
-  - id: cmake-format
-    additional_dependencies: [pyyaml]
-    types: [file]
-    files: (\.cmake|CMakeLists.txt)(.in)?$
-    exclude: ^imcui/third_party/
-
-# Suggested hook if you add a .clang-format file
-- repo: https://github.com/pre-commit/mirrors-clang-format
-  rev: v13.0.0
-  hooks:
-  - id: clang-format
-    exclude: ^imcui/third_party/

CODE_OF_CONDUCT.md

@@ -1,128 +0,0 @@
-# Contributor Covenant Code of Conduct
-
-## Our Pledge
-
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, religion, or sexual identity
-and orientation.
-
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
-
-## Our Standards
-
-Examples of behavior that contributes to a positive environment for our
-community include:
-
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
-  and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the
-  overall community
-
-Examples of unacceptable behavior include:
-
-* The use of sexualized language or imagery, and sexual attention or
-  advances of any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email
-  address, without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Enforcement Responsibilities
-
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
-
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
-
-## Scope
-
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement at
-alpharealcat@gmail.com.
-All complaints will be reviewed and investigated promptly and fairly.
-
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
-
-## Enforcement Guidelines
-
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
-
-### 1. Correction
-
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series
-of actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or
-permanent ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior,  harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within
-the community.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.0, available at
-https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
-
-Community Impact Guidelines were inspired by [Mozilla's code of conduct
-enforcement ladder](https://github.com/mozilla/diversity).
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see the FAQ at
-https://www.contributor-covenant.org/faq. Translations are available at
-https://www.contributor-covenant.org/translations.

Dockerfile

@@ -11,7 +11,7 @@ RUN apt-get update && apt-get install -y git-lfs
 RUN git lfs install
 
 # Clone the Git repository
-RUN git clone --recursive https://github.com/Vincentqyw/image-matching-webui.git /code
+RUN git clone https://huggingface.co/spaces/Realcat/image-matching-webui /code
 
 RUN conda create -n imw python=${PYTHON_VERSION}
 RUN echo "source activate imw" > ~/.bashrc

MANIFEST.in

@@ -1,12 +0,0 @@
-# logo
-include imcui/assets/logo.webp
-
-recursive-include imcui/ui *.yaml
-recursive-include imcui/api *.yaml
-recursive-include imcui/third_party *.yaml *.cfg *.yml
-
-# ui examples
-# recursive-include imcui/datasets *.JPG *.jpg *.png
-
-# model
-recursive-include imcui/third_party/SuperGluePretrainedNetwork *.pth

README.md

@@ -9,93 +9,81 @@ app_file: app.py
 pinned: true
 license: apache-2.0
 ---
+
 [![Contributors][contributors-shield]][contributors-url]
 [![Forks][forks-shield]][forks-url]
 [![Stargazers][stars-shield]][stars-url]
 [![Issues][issues-shield]][issues-url]
 
 <p align="center">
-  <h1 align="center"><br><ins>Image Matching WebUI</ins>
-  <br>Matching Keypoints between two images</h1>
+  <h1 align="center"><br><ins>Image Matching WebUI</ins><br>Identify matching points between two images</h1> 
 </p>
-<div align="center">
-  <a target="_blank" href="https://github.com/Vincentqyw/image-matching-webui/actions/workflows/release.yml"><img src="https://github.com/Vincentqyw/image-matching-webui/actions/workflows/release.yml/badge.svg" alt="PyPI Release"></a>
-  <a target="_blank" href='https://huggingface.co/spaces/Realcat/image-matching-webui'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'></a>
-  <a target="_blank" href="https://pypi.org/project/imcui"><img alt="PyPI - Version" src="https://img.shields.io/pypi/v/imcui?style=flat&logo=pypi&label=imcui&link=https%3A%2F%2Fpypi.org%2Fproject%2Fimcui"></a>
-  <a target="_blank" href="https://hub.docker.com/r/vincentqin/image-matching-webui"><img alt="Docker Image Version" src="https://img.shields.io/docker/v/vincentqin/image-matching-webui?sort=date&arch=amd64&logo=docker&label=imcui&link=https%3A%2F%2Fhub.docker.com%2Fr%2Fvincentqin%2Fimage-matching-webui"></a>
-   <a target="_blank" href="https://pepy.tech/projects/imcui"><img src="https://static.pepy.tech/badge/imcui" alt="PyPI Downloads"></a>
-
-</div>
 
 ## 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](https://gradio.app/). You can effortlessly select two images and a matching algorithm and obtain a precise matching result.
+This simple tool efficiently matches image pairs using multiple famous image matching algorithms. The tool features a Graphical User Interface (GUI) designed using [gradio](https://gradio.app/). 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
-<a href='https://huggingface.co/spaces/Realcat/image-matching-webui'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'></a>
-<a target="_blank" href="https://lightning.ai/realcat/studios/image-matching-webui"><img src="https://pl-bolts-doc-images.s3.us-east-2.amazonaws.com/app-2/studio-badge.svg" alt="Open In Studio"/></a>
+Try it on <a href='https://huggingface.co/spaces/Realcat/image-matching-webui'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'></a> 
+<a target="_blank" href="https://lightning.ai/realcat/studios/image-matching-webui">
+  <img src="https://pl-bolts-doc-images.s3.us-east-2.amazonaws.com/app-2/studio-badge.svg" alt="Open In Studio"/>
+</a>
 
 Here is a demo of the tool:
 
-https://github.com/Vincentqyw/image-matching-webui/assets/18531182/263534692-c3484d1b-cc00-4fdc-9b31-e5b7af07ecd9
+![demo](assets/demo.gif)
 
 The tool currently supports various popular image matching algorithms, namely:
-
-| Algorithm        | Supported | Conference/Journal | Year | GitHub Link |
-|------------------|-----------|--------------------|------|-------------|
-| MINIMA         | ✅ | ARXIV   | 2024 | [Link](https://github.com/LSXI7/MINIMA) |
-| XoFTR          | ✅ | CVPR    | 2024 | [Link](https://github.com/OnderT/XoFTR) |
-| EfficientLoFTR | ✅ | CVPR    | 2024 | [Link](https://github.com/zju3dv/EfficientLoFTR) |
-| MASt3R         | ✅ | CVPR    | 2024 | [Link](https://github.com/naver/mast3r) |
-| DUSt3R         | ✅ | CVPR    | 2024 | [Link](https://github.com/naver/dust3r) |
-| OmniGlue       | ✅ | CVPR    | 2024 | [Link](https://github.com/Vincentqyw/omniglue-onnx) |
-| XFeat          | ✅ | CVPR    | 2024 | [Link](https://github.com/verlab/accelerated_features) |
-| RoMa           | ✅ | CVPR    | 2024 | [Link](https://github.com/Vincentqyw/RoMa) |
-| DeDoDe         | ✅ | 3DV     | 2024 | [Link](https://github.com/Parskatt/DeDoDe) |
-| Mickey         | ❌ | CVPR    | 2024 | [Link](https://github.com/nianticlabs/mickey) |
-| GIM            | ✅ | ICLR    | 2024 | [Link](https://github.com/xuelunshen/gim) |
-| ALIKED         | ✅ | ICCV    | 2023 | [Link](https://github.com/Shiaoming/ALIKED) |
-| LightGlue      | ✅ | ICCV    | 2023 | [Link](https://github.com/cvg/LightGlue) |
-| DarkFeat       | ✅ | AAAI    | 2023 | [Link](https://github.com/THU-LYJ-Lab/DarkFeat) |
-| SFD2           | ✅ | CVPR    | 2023 | [Link](https://github.com/feixue94/sfd2) |
-| IMP            | ✅ | CVPR    | 2023 | [Link](https://github.com/feixue94/imp-release) |
-| ASTR           | ❌ | CVPR    | 2023 | [Link](https://github.com/ASTR2023/ASTR) |
-| SEM            | ❌ | CVPR    | 2023 | [Link](https://github.com/SEM2023/SEM) |
-| DeepLSD        | ❌ | CVPR    | 2023 | [Link](https://github.com/cvg/DeepLSD) |
-| GlueStick      | ✅ | ICCV    | 2023 | [Link](https://github.com/cvg/GlueStick) |
-| ConvMatch      | ❌ | AAAI    | 2023 | [Link](https://github.com/SuhZhang/ConvMatch) |
-| LoFTR          | ✅ | CVPR    | 2021 | [Link](https://github.com/zju3dv/LoFTR) |
-| SOLD2          | ✅ | CVPR    | 2021 | [Link](https://github.com/cvg/SOLD2) |
-| LineTR         | ❌ | RA-L    | 2021 | [Link](https://github.com/yosungho/LineTR) |
-| DKM            | ✅ | CVPR    | 2023 | [Link](https://github.com/Parskatt/DKM) |
-| NCMNet         | ❌ | CVPR    | 2023 | [Link](https://github.com/xinliu29/NCMNet) |
-| TopicFM        | ✅ | AAAI    | 2023 | [Link](https://github.com/Vincentqyw/TopicFM) |
-| AspanFormer    | ✅ | ECCV    | 2022 | [Link](https://github.com/Vincentqyw/ml-aspanformer) |
-| LANet          | ✅ | ACCV    | 2022 | [Link](https://github.com/wangch-g/lanet) |
-| LISRD          | ❌ | ECCV    | 2022 | [Link](https://github.com/rpautrat/LISRD) |
-| REKD           | ❌ | CVPR    | 2022 | [Link](https://github.com/bluedream1121/REKD) |
-| CoTR           | ✅ | ICCV    | 2021 | [Link](https://github.com/ubc-vision/COTR) |
-| ALIKE          | ✅ | TMM     | 2022 | [Link](https://github.com/Shiaoming/ALIKE) |
-| RoRD           | ✅ | IROS    | 2021 | [Link](https://github.com/UditSinghParihar/RoRD) |
-| SGMNet         | ✅ | ICCV    | 2021 | [Link](https://github.com/vdvchen/SGMNet) |
-| SuperPoint     | ✅ | CVPRW   | 2018 | [Link](https://github.com/magicleap/SuperPointPretrainedNetwork) |
-| SuperGlue      | ✅ | CVPR    | 2020 | [Link](https://github.com/magicleap/SuperGluePretrainedNetwork) |
-| D2Net          | ✅ | CVPR    | 2019 | [Link](https://github.com/Vincentqyw/d2-net) |
-| R2D2           | ✅ | NeurIPS | 2019 | [Link](https://github.com/naver/r2d2) |
-| DISK           | ✅ | NeurIPS | 2020 | [Link](https://github.com/cvlab-epfl/disk) |
-| Key.Net        | ❌ | ICCV    | 2019 | [Link](https://github.com/axelBarroso/Key.Net) |
-| OANet          | ❌ | ICCV    | 2019 | [Link](https://github.com/zjhthu/OANet) |
-| SOSNet         | ✅ | CVPR    | 2019 | [Link](https://github.com/scape-research/SOSNet) |
-| HardNet        | ✅ | NeurIPS | 2017 | [Link](https://github.com/DagnyT/hardnet) |
-| SIFT           | ✅ | IJCV    | 2004 | [Link](https://docs.opencv.org/4.x/da/df5/tutorial_py_sift_intro.html) |
-
+- [x] [XoFTR](https://github.com/OnderT/XoFTR), CVPR 2024
+- [x] [EfficientLoFTR](https://github.com/zju3dv/EfficientLoFTR), CVPR 2024
+- [x] [MASt3R](https://github.com/naver/mast3r), CVPR 2024
+- [x] [DUSt3R](https://github.com/naver/dust3r), CVPR 2024
+- [x] [OmniGlue](https://github.com/Vincentqyw/omniglue-onnx), CVPR 2024
+- [x] [XFeat](https://github.com/verlab/accelerated_features), CVPR 2024
+- [x] [RoMa](https://github.com/Vincentqyw/RoMa), CVPR 2024
+- [x] [DeDoDe](https://github.com/Parskatt/DeDoDe), 3DV 2024
+- [ ] [Mickey](https://github.com/nianticlabs/mickey), CVPR 2024
+- [x] [GIM](https://github.com/xuelunshen/gim), ICLR 2024
+- [ ] [DUSt3R](https://github.com/naver/dust3r), arXiv 2023
+- [x] [LightGlue](https://github.com/cvg/LightGlue), ICCV 2023
+- [x] [DarkFeat](https://github.com/THU-LYJ-Lab/DarkFeat), AAAI 2023
+- [x] [SFD2](https://github.com/feixue94/sfd2), CVPR 2023
+- [x] [IMP](https://github.com/feixue94/imp-release), CVPR 2023
+- [ ] [ASTR](https://github.com/ASTR2023/ASTR), CVPR 2023
+- [ ] [SEM](https://github.com/SEM2023/SEM), CVPR 2023
+- [ ] [DeepLSD](https://github.com/cvg/DeepLSD), CVPR 2023
+- [x] [GlueStick](https://github.com/cvg/GlueStick), ICCV 2023
+- [ ] [ConvMatch](https://github.com/SuhZhang/ConvMatch), AAAI 2023
+- [x] [LoFTR](https://github.com/zju3dv/LoFTR), CVPR 2021
+- [x] [SOLD2](https://github.com/cvg/SOLD2), CVPR 2021
+- [ ] [LineTR](https://github.com/yosungho/LineTR), RA-L 2021
+- [x] [DKM](https://github.com/Parskatt/DKM), CVPR 2023
+- [ ] [NCMNet](https://github.com/xinliu29/NCMNet), CVPR 2023
+- [x] [TopicFM](https://github.com/Vincentqyw/TopicFM), AAAI 2023
+- [x] [AspanFormer](https://github.com/Vincentqyw/ml-aspanformer), ECCV 2022
+- [x] [LANet](https://github.com/wangch-g/lanet), ACCV 2022
+- [ ] [LISRD](https://github.com/rpautrat/LISRD), ECCV 2022
+- [ ] [REKD](https://github.com/bluedream1121/REKD), CVPR 2022
+- [x] [CoTR](https://github.com/ubc-vision/COTR), ICCV 2021
+- [x] [ALIKE](https://github.com/Shiaoming/ALIKE), TMM 2022
+- [x] [RoRD](https://github.com/UditSinghParihar/RoRD), IROS 2021
+- [x] [SGMNet](https://github.com/vdvchen/SGMNet), ICCV 2021
+- [x] [SuperPoint](https://github.com/magicleap/SuperPointPretrainedNetwork), CVPRW 2018
+- [x] [SuperGlue](https://github.com/magicleap/SuperGluePretrainedNetwork), CVPR 2020
+- [x] [D2Net](https://github.com/Vincentqyw/d2-net), CVPR 2019
+- [x] [R2D2](https://github.com/naver/r2d2), NeurIPS 2019
+- [x] [DISK](https://github.com/cvlab-epfl/disk), NeurIPS 2020
+- [ ] [Key.Net](https://github.com/axelBarroso/Key.Net), ICCV 2019
+- [ ] [OANet](https://github.com/zjhthu/OANet), ICCV 2019
+- [x] [SOSNet](https://github.com/scape-research/SOSNet), CVPR 2019
+- [x] [HardNet](https://github.com/DagnyT/hardnet), NeurIPS 2017
+- [x] [SIFT](https://docs.opencv.org/4.x/da/df5/tutorial_py_sift_intro.html), IJCV 2004
 
 ## How to use
 
 ### HuggingFace / Lightning AI
 
-Just try it on <a href='https://huggingface.co/spaces/Realcat/image-matching-webui'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'></a>
+Just try it on <a href='https://huggingface.co/spaces/Realcat/image-matching-webui'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'></a> 
 <a target="_blank" href="https://lightning.ai/realcat/studios/image-matching-webui">
   <img src="https://pl-bolts-doc-images.s3.us-east-2.amazonaws.com/app-2/studio-badge.svg" alt="Open In Studio"/>
 </a>
@@ -103,25 +91,11 @@ Just try it on <a href='https://huggingface.co/spaces/Realcat/image-matching-web
 or deploy it locally following the instructions below.
 
 ### Requirements
-
-- [Python 3.9+](https://www.python.org/downloads/)
-
-#### Install from pip [NEW]
-
-Update: now support install from [pip](https://pypi.org/project/imcui), just run:
-
-```bash
-pip install imcui
-```
-
-#### Install from source
-
 ``` bash
 git clone --recursive https://github.com/Vincentqyw/image-matching-webui.git
 cd image-matching-webui
 conda env create -f environment.yaml
 conda activate imw
-pip install -e .
 ```
 
 or using [docker](https://hub.docker.com/r/vincentqin/image-matching-webui):
@@ -130,18 +104,10 @@ or using [docker](https://hub.docker.com/r/vincentqin/image-matching-webui):
 docker pull vincentqin/image-matching-webui:latest
 docker run -it -p 7860:7860 vincentqin/image-matching-webui:latest python app.py --server_name "0.0.0.0" --server_port=7860
 ```
-
-### Deploy to Railway
-
-Deploy to [Railway](https://railway.app/), setting up a `Custom Start Command` in `Deploy` section:
-
-``` bash
-python -m imcui.api.server
-```
-
+ 
 ### Run demo
 ``` bash
-python app.py --config ./config/config.yaml
+python3 ./app.py
 ```
 then open http://localhost:7860 in your browser.
 
@@ -149,54 +115,28 @@ then open http://localhost:7860 in your browser.
 
 ### Add your own feature / matcher
 
-I provide an example to add local feature in [imcui/hloc/extractors/example.py](imcui/hloc/extractors/example.py). Then add feature settings in `confs` in file [imcui/hloc/extract_features.py](imcui/hloc/extract_features.py). Last step is adding some settings to `matcher_zoo` in file [imcui/ui/config.yaml](imcui/ui/config.yaml).
-
-### Upload models
-
-IMCUI hosts all models on [Huggingface](https://huggingface.co/Realcat/imcui_checkpoints).  You can upload your model to Huggingface and add it to the [Realcat/imcui_checkpoints](https://huggingface.co/Realcat/imcui_checkpoints) repository.
-
+I provide an example to add local feature in [hloc/extractors/example.py](hloc/extractors/example.py). Then add feature settings in `confs` in file [hloc/extract_features.py](hloc/extract_features.py). Last step is adding some settings to `model_zoo` in file [ui/config.yaml](ui/config.yaml).
 
 ## Contributions welcome!
 
-External contributions are very much welcome. Please follow the [PEP8 style guidelines](https://www.python.org/dev/peps/pep-0008/) using a linter like flake8. This is a non-exhaustive list of features that might be valuable additions:
+External contributions are very much welcome. Please follow the [PEP8 style guidelines](https://www.python.org/dev/peps/pep-0008/) using a linter like flake8 (reformat using command `python -m black .`). This is a non-exhaustive list of features that might be valuable additions:
 
-- [x] support pip install command
-- [x] add [CPU CI](.github/workflows/ci.yml)
 - [x] add webcam support
 - [x] add [line feature matching](https://github.com/Vincentqyw/LineSegmentsDetection) algorithms
 - [x] example to add a new feature extractor / matcher
 - [x] ransac to filter outliers
-- [ ] add [rotation images](https://github.com/pidahbus/deep-image-orientation-angle-detection) options before matching
+- [ ] add [rotation images](https://github.com/pidahbus/deep-image-orientation-angle-detection) options before matching 
 - [ ] support export matches to colmap ([#issue 6](https://github.com/Vincentqyw/image-matching-webui/issues/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](https://github.com/cvg/GlueStick):
-
-``` bash
-git submodule add https://github.com/cvg/GlueStick.git imcui/third_party/GlueStick
-```
+- [ ] add config file to set default parameters
+- [ ] dynamically load models and reduce GPU overload
 
-If remote submodule repositories are updated, don't forget to pull submodules with:
+Adding local features / matchers as submodules is very easy. For example, to add the [GlueStick](https://github.com/cvg/GlueStick): 
 
 ``` bash
-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 format code before committing, run:
-
-```bash
-pre-commit run -a  # Auto-checks and fixes
+git submodule add https://github.com/cvg/GlueStick.git third_party/GlueStick
 ```
 
-## Contributors
-
-<a href="https://github.com/Vincentqyw/image-matching-webui/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=Vincentqyw/image-matching-webui" />
-</a>
+If remote submodule repositories are updated, don't forget to pull submodules with `git submodule update --remote`, if you only want to update one submodule, use `git submodule update --remote third_party/GlueStick`.
 
 ## Resources
 - [Image Matching: Local Features & Beyond](https://image-matching-workshop.github.io)
@@ -213,4 +153,4 @@ This code is built based on [Hierarchical-Localization](https://github.com/cvg/H
 [stars-shield]: https://img.shields.io/github/stars/Vincentqyw/image-matching-webui.svg?style=for-the-badge
 [stars-url]: https://github.com/Vincentqyw/image-matching-webui/stargazers
 [issues-shield]: https://img.shields.io/github/issues/Vincentqyw/image-matching-webui.svg?style=for-the-badge
-[issues-url]: https://github.com/Vincentqyw/image-matching-webui/issues
+[issues-url]: https://github.com/Vincentqyw/image-matching-webui/issues

{imcui/api → api}/client.py

@@ -120,7 +120,9 @@ def send_request_match(path0: str, path1: str) -> Dict[str, np.ndarray]:
             for key in list(pred.keys()):
                 pred[key] = np.array(pred[key])
         else:
-            print(f"Error: Response code {response.status_code} - {response.text}")
+            print(
+                f"Error: Response code {response.status_code} - {response.text}"
+            )
     finally:
         files["image0"].close()
         files["image1"].close()
@@ -150,8 +152,7 @@ def send_request_extract(
         url=API_URL_EXTRACT,
         **inputs,
     )
-    # breakpoint()
-    # print("Keypoints detected: {}".format(len(response[0]["keypoints"])))
+    print("Keypoints detected: {}".format(len(response[0]["keypoints"])))
 
     # draw matching, debug only
     if viz:
@@ -181,8 +182,6 @@ def get_api_version():
 
 
 if __name__ == "__main__":
-    from pathlib import Path
-
     parser = argparse.ArgumentParser(
         description="Send text to stable audio server and receive generated audio."
     )
@@ -190,19 +189,13 @@ if __name__ == "__main__":
         "--image0",
         required=False,
         help="Path for the file's melody",
-        default=str(
-            Path(__file__).parents[1]
-            / "datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot45.jpg"
-        ),
+        default="datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot45.jpg",
     )
     parser.add_argument(
         "--image1",
         required=False,
         help="Path for the file's melody",
-        default=str(
-            Path(__file__).parents[1]
-            / "datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot90.jpg"
-        ),
+        default="datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot90.jpg",
     )
     args = parser.parse_args()
 
@@ -221,7 +214,7 @@ if __name__ == "__main__":
     #     )
 
     # request extract
-    for i in range(1000):
+    for i in range(10):
         t1 = time.time()
         preds = send_request_extract(args.image0)
         t2 = time.time()

imcui/api/core.py → api/server.py

@@ -1,21 +1,50 @@
-# api.py
+# server.py
+import base64
+import io
+import sys
 import warnings
 from pathlib import Path
-from typing import Any, Dict, Optional
+from typing import Any, Dict, Optional, Union
 
 import cv2
 import matplotlib.pyplot as plt
 import numpy as np
 import torch
+import uvicorn
+from fastapi import FastAPI, File, UploadFile
+from fastapi.exceptions import HTTPException
+from fastapi.responses import JSONResponse
+from PIL import Image
 
-from ..hloc import extract_features, logger, match_dense, match_features
-from ..hloc.utils.viz import add_text, plot_keypoints
-from ..ui.utils import filter_matches, get_feature_model, get_model
-from ..ui.viz import display_matches, fig2im, plot_images
+sys.path.append(str(Path(__file__).parents[1]))
+
+from api.types import ImagesInput
+from hloc import DEVICE, extract_features, logger, match_dense, match_features
+from hloc.utils.viz import add_text, plot_keypoints
+from ui import get_version
+from ui.utils import filter_matches, get_feature_model, get_model
+from ui.viz import display_matches, fig2im, plot_images
 
 warnings.simplefilter("ignore")
 
 
+def decode_base64_to_image(encoding):
+    if encoding.startswith("data:image/"):
+        encoding = encoding.split(";")[1].split(",")[1]
+    try:
+        image = Image.open(io.BytesIO(base64.b64decode(encoding)))
+        return image
+    except Exception as e:
+        logger.warning(f"API cannot decode image: {e}")
+        raise HTTPException(
+            status_code=500, detail="Invalid encoded image"
+        ) from e
+
+
+def to_base64_nparray(encoding: str) -> np.ndarray:
+    return np.array(decode_base64_to_image(encoding)).astype("uint8")
+
+
 class ImageMatchingAPI(torch.nn.Module):
     default_conf = {
         "ransac": {
@@ -58,22 +87,32 @@ class ImageMatchingAPI(torch.nn.Module):
         if device == "cuda":
             memory_allocated = torch.cuda.memory_allocated(device)
             memory_reserved = torch.cuda.memory_reserved(device)
-            logger.info(f"GPU memory allocated: {memory_allocated / 1024**2:.3f} MB")
-            logger.info(f"GPU memory reserved: {memory_reserved / 1024**2:.3f} MB")
+            logger.info(
+                f"GPU memory allocated: {memory_allocated / 1024**2:.3f} MB"
+            )
+            logger.info(
+                f"GPU memory reserved: {memory_reserved / 1024**2:.3f} MB"
+            )
         self.pred = None
 
     def parse_match_config(self, conf):
         if conf["dense"]:
             return {
                 **conf,
-                "matcher": match_dense.confs.get(conf["matcher"]["model"]["name"]),
+                "matcher": match_dense.confs.get(
+                    conf["matcher"]["model"]["name"]
+                ),
                 "dense": True,
             }
         else:
             return {
                 **conf,
-                "feature": extract_features.confs.get(conf["feature"]["model"]["name"]),
-                "matcher": match_features.confs.get(conf["matcher"]["model"]["name"]),
+                "feature": extract_features.confs.get(
+                    conf["feature"]["model"]["name"]
+                ),
+                "matcher": match_features.confs.get(
+                    conf["matcher"]["model"]["name"]
+                ),
                 "dense": False,
             }
 
@@ -86,12 +125,16 @@ class ImageMatchingAPI(torch.nn.Module):
         self.dense = self.conf["dense"]
         if self.conf["dense"]:
             try:
-                self.conf["matcher"]["model"]["match_threshold"] = match_threshold
+                self.conf["matcher"]["model"][
+                    "match_threshold"
+                ] = match_threshold
             except TypeError as e:
                 logger.error(e)
         else:
             self.conf["feature"]["model"]["max_keypoints"] = max_keypoints
-            self.conf["feature"]["model"]["keypoint_threshold"] = detect_threshold
+            self.conf["feature"]["model"][
+                "keypoint_threshold"
+            ] = detect_threshold
             self.extract_conf = self.conf["feature"]
 
         self.match_conf = self.conf["matcher"]
@@ -127,17 +170,6 @@ class ImageMatchingAPI(torch.nn.Module):
             pred = match_features.match_images(self.matcher, pred0, pred1)
         return pred
 
-    def _convert_pred(self, pred):
-        ret = {
-            k: v.cpu().detach()[0].numpy() if isinstance(v, torch.Tensor) else v
-            for k, v in pred.items()
-        }
-        ret = {
-            k: v[0].cpu().detach().numpy() if isinstance(v, list) else v
-            for k, v in ret.items()
-        }
-        return ret
-
     @torch.inference_mode()
     def extract(self, img0: np.ndarray, **kwargs) -> Dict[str, np.ndarray]:
         """Extract features from a single image.
@@ -158,13 +190,17 @@ class ImageMatchingAPI(torch.nn.Module):
         pred = extract_features.extract(
             self.extractor, img0, self.extract_conf["preprocessing"]
         )
-        pred = self._convert_pred(pred)
+        pred = {
+            k: v.cpu().detach()[0].numpy() if isinstance(v, torch.Tensor) else v
+            for k, v in pred.items()
+        }
         # back to origin scale
         s0 = pred["original_size"] / pred["size"]
         pred["keypoints_orig"] = (
             match_features.scale_keypoints(pred["keypoints"] + 0.5, s0) - 0.5
         )
         # TODO: rotate back
+
         binarize = kwargs.get("binarize", False)
         if binarize:
             assert "descriptors" in pred
@@ -263,7 +299,10 @@ class ImageMatchingAPI(torch.nn.Module):
         output_keypoints: np.ndarray = plot_images(
             [image0, image1], titles=titles, dpi=300
         )
-        if "keypoints0_orig" in pred.keys() and "keypoints1_orig" in pred.keys():
+        if (
+            "keypoints0_orig" in pred.keys()
+            and "keypoints1_orig" in pred.keys()
+        ):
             plot_keypoints([pred["keypoints0_orig"], pred["keypoints1_orig"]])
             text: str = (
                 f"# keypoints0: {len(pred['keypoints0_orig'])} \n"
@@ -289,7 +328,9 @@ class ImageMatchingAPI(torch.nn.Module):
         )
         if log_path is not None:
             img_keypoints_path: Path = log_path / f"img_keypoints_{postfix}.png"
-            img_matches_raw_path: Path = log_path / f"img_matches_raw_{postfix}.png"
+            img_matches_raw_path: Path = (
+                log_path / f"img_matches_raw_{postfix}.png"
+            )
             img_matches_ransac_path: Path = (
                 log_path / f"img_matches_ransac_{postfix}.png"
             )
@@ -306,3 +347,153 @@ class ImageMatchingAPI(torch.nn.Module):
                 output_matches_ransac[:, :, ::-1].copy(),  # RGB -> BGR
             )
             plt.close("all")
+
+
+class ImageMatchingService:
+    def __init__(self, conf: dict, device: str):
+        self.conf = conf
+        self.api = ImageMatchingAPI(conf=conf, device=device)
+        self.app = FastAPI()
+        self.register_routes()
+
+    def register_routes(self):
+
+        @self.app.get("/version")
+        async def version():
+            return {"version": get_version()}
+
+        @self.app.post("/v1/match")
+        async def match(
+            image0: UploadFile = File(...), image1: UploadFile = File(...)
+        ):
+            """
+            Handle the image matching request and return the processed result.
+
+            Args:
+                image0 (UploadFile): The first image file for matching.
+                image1 (UploadFile): The second image file for matching.
+
+            Returns:
+                JSONResponse: A JSON response containing the filtered match results
+                              or an error message in case of failure.
+            """
+            try:
+                # Load the images from the uploaded files
+                image0_array = self.load_image(image0)
+                image1_array = self.load_image(image1)
+
+                # Perform image matching using the API
+                output = self.api(image0_array, image1_array)
+
+                # Keys to skip in the output
+                skip_keys = ["image0_orig", "image1_orig"]
+
+                # Postprocess the output to filter unwanted data
+                pred = self.postprocess(output, skip_keys)
+
+                # Return the filtered prediction as a JSON response
+                return JSONResponse(content=pred)
+            except Exception as e:
+                # Return an error message with status code 500 in case of exception
+                return JSONResponse(content={"error": str(e)}, status_code=500)
+
+        @self.app.post("/v1/extract")
+        async def extract(input_info: ImagesInput):
+            """
+            Extract keypoints and descriptors from images.
+
+            Args:
+                input_info: An object containing the image data and options.
+
+            Returns:
+                A list of dictionaries containing the keypoints and descriptors.
+            """
+            try:
+                preds = []
+                for i, input_image in enumerate(input_info.data):
+                    # Load the image from the input data
+                    image_array = to_base64_nparray(input_image)
+                    # Extract keypoints and descriptors
+                    output = self.api.extract(
+                        image_array,
+                        max_keypoints=input_info.max_keypoints[i],
+                        binarize=input_info.binarize,
+                    )
+                    # Do not return the original image and image_orig
+                    # skip_keys = ["image", "image_orig"]
+                    skip_keys = []
+
+                    # Postprocess the output
+                    pred = self.postprocess(output, skip_keys)
+                    preds.append(pred)
+                # Return the list of extracted features
+                return JSONResponse(content=preds)
+            except Exception as e:
+                # Return an error message if an exception occurs
+                return JSONResponse(content={"error": str(e)}, status_code=500)
+
+    def load_image(self, file_path: Union[str, UploadFile]) -> np.ndarray:
+        """
+        Reads an image from a file path or an UploadFile object.
+
+        Args:
+            file_path: A file path or an UploadFile object.
+
+        Returns:
+            A numpy array representing the image.
+        """
+        if isinstance(file_path, str):
+            file_path = Path(file_path).resolve(strict=False)
+        else:
+            file_path = file_path.file
+        with Image.open(file_path) as img:
+            image_array = np.array(img)
+        return image_array
+
+    def postprocess(
+        self, output: dict, skip_keys: list, binarize: bool = True
+    ) -> dict:
+        pred = {}
+        for key, value in output.items():
+            if key in skip_keys:
+                continue
+            if isinstance(value, np.ndarray):
+                pred[key] = value.tolist()
+        return pred
+
+    def run(self, host: str = "0.0.0.0", port: int = 8001):
+        uvicorn.run(self.app, host=host, port=port)
+
+
+if __name__ == "__main__":
+    conf = {
+        "feature": {
+            "output": "feats-superpoint-n4096-rmax1600",
+            "model": {
+                "name": "superpoint",
+                "nms_radius": 3,
+                "max_keypoints": 4096,
+                "keypoint_threshold": 0.005,
+            },
+            "preprocessing": {
+                "grayscale": True,
+                "force_resize": True,
+                "resize_max": 1600,
+                "width": 640,
+                "height": 480,
+                "dfactor": 8,
+            },
+        },
+        "matcher": {
+            "output": "matches-NN-mutual",
+            "model": {
+                "name": "nearest_neighbor",
+                "do_mutual_check": True,
+                "match_threshold": 0.2,
+            },
+        },
+        "dense": False,
+    }
+
+    service = ImageMatchingService(conf=conf, device=DEVICE)
+    service.run()

{imcui/api → api}/test/CMakeLists.txt

@@ -6,12 +6,11 @@ find_package(OpenCV REQUIRED)
 
 find_package(Boost REQUIRED COMPONENTS system)
 if(Boost_FOUND)
-  include_directories(${Boost_INCLUDE_DIRS})
+    include_directories(${Boost_INCLUDE_DIRS})
 endif()
 
 add_executable(client client.cpp)
 
-target_include_directories(client PRIVATE ${Boost_LIBRARIES}
-                                          ${OpenCV_INCLUDE_DIRS})
+target_include_directories(client PRIVATE ${Boost_LIBRARIES} ${OpenCV_INCLUDE_DIRS})
 
 target_link_libraries(client PRIVATE curl jsoncpp b64 ${OpenCV_LIBS})

{imcui/api → api}/test/client.cpp

@@ -3,8 +3,7 @@
 #include "helper.h"
 
 int main() {
-    std::string img_path =
-        "../../../datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot45.jpg";
+    std::string img_path = "../../../datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot45.jpg";
     cv::Mat original_img = cv::imread(img_path, cv::IMREAD_GRAYSCALE);
 
     if (original_img.empty()) {
@@ -28,19 +27,23 @@ int main() {
     }
 
     // construct params
-    APIParams params{.data = {base64_img},
-                     .max_keypoints = {100, 100},
-                     .timestamps = {"0", "1"},
-                     .grayscale = {0},
-                     .image_hw = {{480, 640}, {240, 320}},
-                     .feature_type = 0,
-                     .rotates = {0.0f, 0.0f},
-                     .scales = {1.0f, 1.0f},
-                     .reference_points = {{1.23e+2f, 1.2e+1f},
-                                          {5.0e-1f, 3.0e-1f},
-                                          {2.3e+2f, 2.2e+1f},
-                                          {6.0e-1f, 4.0e-1f}},
-                     .binarize = {1}};
+    APIParams params{
+        .data = {base64_img},
+        .max_keypoints = {100, 100},
+        .timestamps = {"0", "1"},
+        .grayscale = {0},
+        .image_hw = {{480, 640}, {240, 320}},
+        .feature_type = 0,
+        .rotates = {0.0f, 0.0f},
+        .scales = {1.0f, 1.0f},
+        .reference_points = {
+            {1.23e+2f, 1.2e+1f},
+            {5.0e-1f, 3.0e-1f},
+            {2.3e+2f, 2.2e+1f},
+            {6.0e-1f, 4.0e-1f}
+        },
+        .binarize = {1}
+    };
 
     KeyPointResults kpts_results;
 
@@ -67,11 +70,11 @@ int main() {
         res = curl_easy_perform(curl);
 
         if (res != CURLE_OK)
-            fprintf(
-                stderr, "curl_easy_perform() failed: %s\n", curl_easy_strerror(res));
+            fprintf(stderr, "curl_easy_perform() failed: %s\n",
+                    curl_easy_strerror(res));
         else {
             // std::cout << "Response from server: " << readBuffer << std::endl;
-            kpts_results = decode_response(readBuffer);
+           kpts_results =  decode_response(readBuffer);
         }
         curl_easy_cleanup(curl);
     }

{imcui/api → api}/test/helper.h

@@ -1,15 +1,15 @@
 
-#include <b64/encode.h>
+#include <sstream>
 #include <fstream>
+#include <vector>
+#include <b64/encode.h>
 #include <jsoncpp/json/json.h>
 #include <opencv2/opencv.hpp>
-#include <sstream>
-#include <vector>
 
 // base64 to image
-#include <boost/archive/iterators/base64_from_binary.hpp>
 #include <boost/archive/iterators/binary_from_base64.hpp>
 #include <boost/archive/iterators/transform_width.hpp>
+#include <boost/archive/iterators/base64_from_binary.hpp>
 
 /// Parameters used in the API
 struct APIParams {
@@ -50,19 +50,17 @@ struct APIParams {
  * @details Stores the keypoints and descriptors for each image.
  */
 class KeyPointResults {
-      public:
-    KeyPointResults() {
-    }
+public:
+    KeyPointResults() {}
 
     /**
      * @brief Constructor.
      *
      * @param kp The keypoints for each image.
      */
-    KeyPointResults(const std::vector<std::vector<cv::KeyPoint>>& kp,
+    KeyPointResults(const std::vector<std::vector<cv::KeyPoint>>& kp, 
                     const std::vector<cv::Mat>& desc)
-        : keypoints(kp), descriptors(desc) {
-    }
+        : keypoints(kp), descriptors(desc) {}
 
     /**
      * @brief Append keypoints to the result.
@@ -100,12 +98,13 @@ class KeyPointResults {
         return descriptors;
     }
 
-      private:
+private:
     std::vector<std::vector<cv::KeyPoint>> keypoints;
     std::vector<cv::Mat> descriptors;
     std::vector<std::vector<float>> scores;
 };
 
+
 /**
  * @brief Decodes a base64 encoded string.
  *
@@ -127,6 +126,8 @@ std::string base64_decode(const std::string& base64) {
     return std::string(It(base64.begin()), It(base64.begin() + end));
 }
 
+
+
 /**
  * @brief Decodes a base64 string into an OpenCV image
  *
@@ -149,6 +150,7 @@ cv::Mat base64_to_image(const std::string& base64) {
     return img;
 }
 
+
 /**
  * @brief Encodes an OpenCV image into a base64 string
  *
@@ -161,7 +163,7 @@ cv::Mat base64_to_image(const std::string& base64) {
  *
  * @throws std::runtime_error if the image is empty or encoding fails
  */
-std::string image_to_base64(cv::Mat& img) {
+std::string image_to_base64(cv::Mat &img) {
     if (img.empty()) {
         throw std::runtime_error("Failed to read image");
     }
@@ -174,8 +176,7 @@ std::string image_to_base64(cv::Mat& img) {
 
     // Encode the bytes as a base64 string
     using namespace boost::archive::iterators;
-    using It =
-        base64_from_binary<transform_width<std::vector<uchar>::const_iterator, 6, 8>>;
+    using It = base64_from_binary<transform_width<std::vector<uchar>::const_iterator, 6, 8>>;
     std::string base64(It(buf.begin()), It(buf.end()));
 
     // Pad the string with '=' characters to a multiple of 4 bytes
@@ -184,6 +185,7 @@ std::string image_to_base64(cv::Mat& img) {
     return base64;
 }
 
+
 /**
  * @brief Callback function for libcurl to write data to a string
  *
@@ -225,7 +227,8 @@ size_t WriteCallback(void* contents, size_t size, size_t nmemb, std::string* s)
  * @param val The value to convert
  * @return The converted Json::Value
  */
-template <typename T> Json::Value toJson(const T& val) {
+template <typename T>
+Json::Value toJson(const T& val) {
     return Json::Value(val);
 }
 
@@ -238,7 +241,8 @@ template <typename T> Json::Value toJson(const T& val) {
  * @param vec The vector to convert to Json::Value
  * @return The Json::Value representing the vector
  */
-template <typename T> Json::Value vectorToJson(const std::vector<T>& vec) {
+template <typename T>
+Json::Value vectorToJson(const std::vector<T>& vec) {
     Json::Value json(Json::arrayValue);
     for (const auto& item : vec) {
         json.append(item);
@@ -249,9 +253,8 @@ template <typename T> Json::Value vectorToJson(const std::vector<T>& vec) {
 /**
  * @brief Converts a nested vector to a Json::Value
  *
- * This function takes a nested vector of type T and converts it to a
- * Json::Value. Each sub-vector is converted to a Json::Value array and appended
- * to the main Json::Value array.
+ * This function takes a nested vector of type T and converts it to a Json::Value.
+ * Each sub-vector is converted to a Json::Value array and appended to the main Json::Value array.
  *
  * @param vec The nested vector to convert to Json::Value
  * @return The Json::Value representing the nested vector
@@ -265,23 +268,22 @@ Json::Value nestedVectorToJson(const std::vector<std::vector<T>>& vec) {
     return json;
 }
 
+
+
 /**
  * @brief Converts the APIParams struct to a Json::Value
  *
  * This function takes an APIParams struct and converts it to a Json::Value.
  * The Json::Value is a JSON object with the following fields:
  * - data: a JSON array of base64 encoded images
- * - max_keypoints: a JSON array of integers, max number of keypoints for each
- * image
+ * - max_keypoints: a JSON array of integers, max number of keypoints for each image
  * - timestamps: a JSON array of timestamps, one for each image
  * - grayscale: a JSON boolean, whether to convert images to grayscale
- * - image_hw: a nested JSON array, each sub-array contains the height and width
- * of an image
+ * - image_hw: a nested JSON array, each sub-array contains the height and width of an image
  * - feature_type: a JSON integer, the type of feature detector to use
  * - rotates: a JSON array of doubles, the rotation of each image
  * - scales: a JSON array of doubles, the scale of each image
- * - reference_points: a nested JSON array, each sub-array contains the
- * reference points of an image
+ * - reference_points: a nested JSON array, each sub-array contains the reference points of an image
  * - binarize: a JSON boolean, whether to binarize the descriptors
  *
  * @param params The APIParams struct to convert
@@ -302,7 +304,8 @@ Json::Value paramsToJson(const APIParams& params) {
     return json;
 }
 
-template <typename T> cv::Mat jsonToMat(Json::Value json) {
+template<typename T>
+cv::Mat jsonToMat(Json::Value json) {
     int rows = json.size();
     int cols = json[0].size();
 
@@ -317,14 +320,14 @@ template <typename T> cv::Mat jsonToMat(Json::Value json) {
     }
 
     // Create a cv::Mat object that points to the data.
-    cv::Mat mat(rows, cols, CV_8UC1,
-                data.data());  // Change the type if necessary.
-    // cv::Mat mat(cols, rows,CV_8UC1, data.data());  // Change the type if
-    // necessary.
+    cv::Mat mat(rows, cols, CV_8UC1, data.data());  // Change the type if necessary.
+    // cv::Mat mat(cols, rows,CV_8UC1, data.data());  // Change the type if necessary.
 
     return mat;
 }
 
+
+
 /**
  * @brief Decodes the response of the server and prints the keypoints
  *
@@ -334,7 +337,7 @@ template <typename T> cv::Mat jsonToMat(Json::Value json) {
  * @param response The response of the server
  * @return The keypoints and descriptors
  */
-KeyPointResults decode_response(const std::string& response, bool viz = true) {
+KeyPointResults decode_response(const std::string& response, bool viz=true) {
     Json::CharReaderBuilder builder;
     Json::CharReader* reader = builder.newCharReader();
 
@@ -342,8 +345,8 @@ KeyPointResults decode_response(const std::string& response, bool viz = true) {
     std::string errors;
 
     // Parse the JSON response
-    bool parsingSuccessful = reader->parse(
-        response.c_str(), response.c_str() + response.size(), &jsonData, &errors);
+    bool parsingSuccessful = reader->parse(response.c_str(),
+        response.c_str() + response.size(), &jsonData, &errors);
     delete reader;
 
     if (!parsingSuccessful) {
@@ -373,23 +376,25 @@ KeyPointResults decode_response(const std::string& response, bool viz = true) {
         for (const auto& keypoint : jkeypoints_orig) {
             if (counter < 10) {
                 // Print the first 10 keypoints
-                std::cout << keypoint[0].asFloat() << ", " << keypoint[1].asFloat()
-                          << std::endl;
+                std::cout << keypoint[0].asFloat() << ", "
+                    << keypoint[1].asFloat() << std::endl;
             }
             counter++;
             // Convert the Json::Value to a cv::KeyPoint
-            vkeypoints.emplace_back(
-                cv::KeyPoint(keypoint[0].asFloat(), keypoint[1].asFloat(), 0.0));
+            vkeypoints.emplace_back(cv::KeyPoint(keypoint[0].asFloat(),
+                keypoint[1].asFloat(), 0.0));
         }
 
         if (viz && jsonItem.isMember("image_orig")) {
+
             auto jimg_orig = jsonItem["image_orig"];
             cv::Mat img = jsonToMat<uchar>(jimg_orig);
             cv::imwrite("viz_image_orig.jpg", img);
 
             // Draw keypoints on the image
             cv::Mat imgWithKeypoints;
-            cv::drawKeypoints(img, vkeypoints, imgWithKeypoints, cv::Scalar(0, 0, 255));
+            cv::drawKeypoints(img, vkeypoints, 
+                imgWithKeypoints, cv::Scalar(0, 0, 255));
 
             // Write the image with keypoints
             std::string filename = "viz_image_orig_keypoints.jpg";
@@ -397,7 +402,7 @@ KeyPointResults decode_response(const std::string& response, bool viz = true) {
         }
 
         // Iterate over the descriptors
-        cv::Mat descriptors = jsonToMat<uchar>(jdescriptors);
+        cv::Mat descriptors = jsonToMat<uchar>(jdescriptors); 
         kpts_results.append_keypoints(vkeypoints);
         kpts_results.append_descriptors(descriptors);
     }

imcui/api/__init__.py → api/types.py

@@ -1,15 +1,7 @@
-import base64
-import io
 from typing import List
 
-import numpy as np
-from fastapi.exceptions import HTTPException
-from PIL import Image
 from pydantic import BaseModel
 
-from ..hloc import logger
-from .core import ImageMatchingAPI
-
 
 class ImagesInput(BaseModel):
     data: List[str] = []
@@ -22,26 +14,3 @@ class ImagesInput(BaseModel):
     scales: List[float] = []
     reference_points: List[List[float]] = []
     binarize: bool = False
-
-
-def decode_base64_to_image(encoding):
-    if encoding.startswith("data:image/"):
-        encoding = encoding.split(";")[1].split(",")[1]
-    try:
-        image = Image.open(io.BytesIO(base64.b64decode(encoding)))
-        return image
-    except Exception as e:
-        logger.warning(f"API cannot decode image: {e}")
-        raise HTTPException(status_code=500, detail="Invalid encoded image") from e
-
-
-def to_base64_nparray(encoding: str) -> np.ndarray:
-    return np.array(decode_base64_to_image(encoding)).astype("uint8")
-
-
-__all__ = [
-    "ImageMatchingAPI",
-    "ImagesInput",
-    "decode_base64_to_image",
-    "to_base64_nparray",
-]

app.py

@@ -1,6 +1,6 @@
 import argparse
 from pathlib import Path
-from imcui.ui.app_class import ImageMatchingApp
+from ui.app_class import ImageMatchingApp
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
@@ -19,13 +19,10 @@ if __name__ == "__main__":
     parser.add_argument(
         "--config",
         type=str,
-        default=Path(__file__).parent / "config/config.yaml",
+        default=Path(__file__).parent / "ui/config.yaml",
         help="config file",
     )
     args = parser.parse_args()
     ImageMatchingApp(
-        args.server_name,
-        args.server_port,
-        config=args.config,
-        example_data_root=Path("imcui/datasets"),
+        args.server_name, args.server_port, config=args.config
     ).run()

build_docker.sh

@@ -1,3 +1,3 @@
 docker build -t image-matching-webui:latest . --no-cache
 docker tag image-matching-webui:latest vincentqin/image-matching-webui:latest
-docker push vincentqin/image-matching-webui:latest
+docker push vincentqin/image-matching-webui:latest