Git Product home page Git Product logo

keypoints's Introduction

Memo

Install pytorch==1.11.

Bug: If you import packages following order:

import torch
import build.fivep as f

I got the following error.

    import build.fivep as f                                                  
ImportError: /usr/lib/x86_64-linux-gnu/libstdc++.so.6: version `GLIBCXX_3.4.30' not found (required by /home/komatsu/anaconda3/envs/py37-keypoints/lib/libopencv_core.so.405)  

However, if I import fivep first, I didn't get any error.

import build.fivep as f
import torch

---- Original Readme ----

Keypoints

This is the official repository of the OMNICV-CVPR2022 workshop named "Pose Estimation for Two-View Panoramas: a Comparative Analysis"

Visit our paper:

IEEE link

CVF access

Installation

  1. Create a conda enviorenment
conda create --name py37-keypoints python=3.7
conda activate py37-keypoints
  1. Install the Spherical Package from Meder github

  2. Git clone the project and enter the folder

git clone https://github.com/Artcs1/Keypoints.git
cd Keypoints
  1. Install the requirements
pip install -r requirements.txt
  1. Install liegroups package in utils directory

  2. Compile the SPHORB package

cd SPHORB-master
conda create --name SPHORB python=3.7
conda activate SPHORB
conda install -c conda-forge opencv==3.4.2
mkdir build1
cd build1
cmake ..
make
conda deactivate
  1. Compile the five-point algorithm package
cd fivepoint
conda create --name FP python=3.7
conda activate FP
conda install -c conda-forge opencv==4.5.5
mkdir build
cd build
cmake ..
make
conda deactivate

Usage

  1. Activate the conda enviorenment
conda activate py37-keypoints
  1. Run extrack_keypoints.py file
python3 extract_keypoints.py --datas [Urban1|Urban2|Urban3|Urban4|Room|Classroom|Realistic|Interior1|Interior2] --descriptors [sift|tsift|orb|torb|spoint|tspoint|sphorb]
  1. Example for Outdoor dataset
python3 extract_keypoints.py --datas Urban1 Urban2 Urban3 Urban4 --descriptors  orb torb sift tsift spoint tspoint sphorb
  1. Example for Indoor dataset
python3 extract_keypoints.py --datas Room Classroom Realistic Interior1 Interior2 --descriptors  orb torb sift tsift spoint tspoint sphorb

Visual example

python3 show_keypoints.py --descriptor sift

Keypoints

Benchmark and results

100 images per dataset

Downloand link

Indoor Outdoor

1000 images per dataset

Downloand link

Cite our work

@InProceedings{Murrugarra-Llerena_2022_CVPR,
    author    = {Murrugarra-Llerena, Jeffri and da Silveira, Thiago L. T. and Jung, Claudio R.},
    title     = {Pose Estimation for Two-View Panoramas Based on Keypoint Matching: A Comparative Study and Critical Analysis},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2022},
    pages     = {5202-5211}
}

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.