Skip to content

[ECCV-2020 (spotlight)] Self-supervising Fine-grained Region Similarities for Large-scale Image Localization. 🌏 PyTorch open-source toolbox for image-based localization (place recognition).

License

yxgeee/OpenIBL

master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
ibl
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

OpenIBL

Introduction

OpenIBL is an open-source PyTorch-based codebase for image-based localization, or in other words, place recognition. It supports multiple state-of-the-art methods, and also covers the official implementation for our ECCV-2020 spotlight paper SFRS. We support single/multi-node multi-gpu distributed training and testing, launched by slurm or pytorch.

Official implementation:

  • SFRS: Self-supervising Fine-grained Region Similarities for Large-scale Image Localization (ECCV'20 Spotlight) [paper] [Blog(Chinese)]

Unofficial implementation:

FAQ

Quick Start without Installation

Extract descriptor for a single image

import torch
from torchvision import transforms
from PIL import Image

# load the best model with PCA (trained by our SFRS)
model = torch.hub.load('yxgeee/OpenIBL', 'vgg16_netvlad', pretrained=True).eval()

# read image
img = Image.open('image.jpg').convert('RGB') # modify the image path according to your need
transformer = transforms.Compose([transforms.Resize((480, 640)), # (height, width)
                                  transforms.ToTensor(),
                                  transforms.Normalize(mean=[0.48501960784313836, 0.4579568627450961, 0.4076039215686255],
                                                       std=[0.00392156862745098, 0.00392156862745098, 0.00392156862745098])])
img = transformer(img)

# use GPU (optional)
model = model.cuda()
img = img.cuda()

# extract descriptor (4096-dim)
with torch.no_grad():
    des = model(img.unsqueeze(0))[0]
des = des.cpu().numpy()

Installation

Please refer to INSTALL.md for installation and dataset preparation.

Train & Test

To reproduce the results in papers, you could train and test the models following the instruction in REPRODUCTION.md.

Model Zoo

Please refer to MODEL_ZOO.md for trained models.

License

OpenIBL is released under the MIT license.

Citation

If you find this repo useful for your research, please consider citing the paper

@inproceedings{ge2020self,
    title={Self-supervising Fine-grained Region Similarities for Large-scale Image Localization},
    author={Yixiao Ge and Haibo Wang and Feng Zhu and Rui Zhao and Hongsheng Li},
    booktitle={European Conference on Computer Vision}
    year={2020},
}

Acknowledgements

The structure of this repo is inspired by open-reid, and part of the code is inspired by pytorch-NetVlad.

About

[ECCV-2020 (spotlight)] Self-supervising Fine-grained Region Similarities for Large-scale Image Localization. 🌏 PyTorch open-source toolbox for image-based localization (place recognition).

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published