Image Matching Evaluation

Related tags

Deep Learning IME
Overview

Image Matching Evaluation (IME)

IME provides to test any feature matching algorithm on datasets containing ground-truth homographies.

Also, one can reproduce the results given in our paper Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods published in ICCV 2021 TradiCV Workshop.

Currently Supported Algorithms

Classical Learning-Based
SIFT SuperPoint
SURF SuperGlue
ORB Patch2Pix
KAZE DFM
AKAZE

Environment Setup

This repository is created using Anaconda.

Open a terminal in the IME folder and run the following commands;

  1. Run bash script to create environment for IME, download algorithms and datasets
bash install.sh
  1. Activate the environment
conda activate ime
  1. Run IME!
python3 main.ipy

Well done, you can find results on Results folder :)

Notes:

  1. For DFM algorithm you can arrange ratio test threshold using DFM/python/algorithm_wrapper_util.py by changing ratio_th (default = [0.9, 0.9, 0.9, 0.9, 0.95, 1.0]).

    For all classical algorithms you can arrange ratio test threshold by changing the ratio parameter of mnn_ratio_matcher function in algorithm_wrapper_util.py for each algortihm.

    For SuperPoint again you should change ratio parameter of mnn_ratio_matcher function in algorithm_wrapper.py

    For Patch2Pix you should change io_thres parameter in algorithm_wrapper_util.py

  2. Use get_names.py to select algorithms and datasets.

  3. You can put your own algorithm on Algorithm folder to evaluate with creating a wrapper with the same format. This wrapper should output the matched pixel positions between two images using the selected algorithm.

  4. You can put your own dataset on Dataset folder to evaluate by arranging the proper format. Dataset should be in the form of Dataset/subset/subsubset/

Reproducing Results Given in our Paper

We provide the results given in our paper in ICCV_Results folder. To reproduce the results, you can run an experiment for a specific ratio test or confidence threshold and copy the results in the relevant ratio threshold folder in hpatches_classical or hpatches_deep folder. Then, you can run rt_fig.py and auc_fig.py scripts to save and view the figures.

TODO

Algorithms to be added:

Datasets to be added:

BibTeX Citation

Please cite our paper if you use the code:

@InProceedings{Efe_2021_ICCV,
    author    = {Efe, Ufuk and Ince, Kutalmis Gokalp and Alatan, Aydin},
    title     = {Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
    month     = {October},
    year      = {2021},
}
You might also like...
Source code for the GPT-2 story generation models in the EMNLP 2020 paper "STORIUM: A Dataset and Evaluation Platform for Human-in-the-Loop Story Generation"

Storium GPT-2 Models This is the official repository for the GPT-2 models described in the EMNLP 2020 paper [STORIUM: A Dataset and Evaluation Platfor

Provided is code that demonstrates the training and evaluation of the work presented in the paper:
Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face Manipulation" published in CVPR 2020.

FFD Source Code Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face M

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.
[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

MiVOS (CVPR 2021) - Mask Propagation Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang [arXiv] [Paper PDF] [Project Page] [Papers with Code] This repo impleme

An evaluation toolkit for voice conversion models.

Voice-conversion-evaluation An evaluation toolkit for voice conversion models. Sample test pair Generate the metadata for evaluating models. The direc

QuanTaichi evaluation suite
QuanTaichi evaluation suite

QuanTaichi: A Compiler for Quantized Simulations (SIGGRAPH 2021) Yuanming Hu, Jiafeng Liu, Xuanda Yang, Mingkuan Xu, Ye Kuang, Weiwei Xu, Qiang Dai, W

Evaluation Pipeline for our ECCV2020: Journey Towards Tiny Perceptual Super-Resolution.

Journey Towards Tiny Perceptual Super-Resolution Test code for our ECCV2020 paper: https://arxiv.org/abs/2007.04356 Our x4 upscaling pre-trained model

 PyTorch evaluation code for Delving Deep into the Generalization of Vision Transformers under Distribution Shifts.
PyTorch evaluation code for Delving Deep into the Generalization of Vision Transformers under Distribution Shifts.

Out-of-distribution Generalization Investigation on Vision Transformers This repository contains PyTorch evaluation code for Delving Deep into the Gen

A large-scale video dataset for the training and evaluation of 3D human pose estimation models
A large-scale video dataset for the training and evaluation of 3D human pose estimation models

ASPset-510 ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation mode

A large-scale video dataset for the training and evaluation of 3D human pose estimation models
A large-scale video dataset for the training and evaluation of 3D human pose estimation models

ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation models. It contains 17 different amateur subjects performing 30 sports-related actions each, for a total of 510 action clips.

Comments
  • match_pairs_sp.py

    match_pairs_sp.py

    Thank you for your excellent work. But I can't find match_pairs_sp.py in utils/Algorithm_Wrappers/SuperPoint. Can you help me solve this problem? Thank you.

    opened by githubhupan 2
Owner
PhD student @ METU
null
Code for C2-Matching (CVPR2021). Paper: Robust Reference-based Super-Resolution via C2-Matching.

C2-Matching (CVPR2021) This repository contains the implementation of the following paper: Robust Reference-based Super-Resolution via C2-Matching Yum

Yuming Jiang 151 Dec 26, 2022
This project uses Template Matching technique for object detecting by detection of template image over base image.

Object Detection Project Using OpenCV This project uses Template Matching technique for object detecting by detection the template image over base ima

Pratham Bhatnagar 7 May 29, 2022
This project uses Template Matching technique for object detecting by detection of template image over base image

Object Detection Project Using OpenCV This project uses Template Matching technique for object detecting by detection the template image over base ima

Pratham Bhatnagar 4 Nov 16, 2021
Framework for joint representation learning, evaluation through multimodal registration and comparison with image translation based approaches

CoMIR: Contrastive Multimodal Image Representation for Registration Framework ?? Registration of images in different modalities with Deep Learning ??

Methods for Image Data Analysis - MIDA 55 Dec 9, 2022
The code of “Similarity Reasoning and Filtration for Image-Text Matching” [AAAI2021]

SGRAF PyTorch implementation for AAAI2021 paper of “Similarity Reasoning and Filtration for Image-Text Matching”. It is built on top of the SCAN and C

Ronnie_IIAU 149 Dec 22, 2022
MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR2021)

MASA-SR Official PyTorch implementation of our CVPR2021 paper MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Re

DV Lab 126 Dec 20, 2022
CNN Based Meta-Learning for Noisy Image Classification and Template Matching

CNN Based Meta-Learning for Noisy Image Classification and Template Matching Introduction This master thesis used a few-shot meta learning approach to

Kumar Manas 2 Dec 9, 2021
Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave

Note: the current releases of this toolbox are a beta release, to test working with Haskell's, Python's, and R's code repositories. Metrics provides i

Ben Hamner 1.6k Dec 26, 2022
Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.

Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy. Now with tensorflow 1.0 support. Evaluation usa

Marcel R. 349 Aug 6, 2022