GitHub - AaltoVision/DGC-Net: A PyTorch implementation of "DGC-Net: Dense G...
source link: https://github.com/AaltoVision/DGC-Net
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
DGC-Net: Dense Geometric Correspondence Network
This is a PyTorch implementation of our work "DGC-Net: Dense Geometric Correspondence Network"
TL;DR A CNN-based approach to obtain dense pixel correspondences between two views.
Installation
- create and activate conda environment with Python 3.x
conda create -n my_fancy_env python=3.7
source activate my_fancy_env
- install Pytorch v1.0.0 and torchvision library
pip install torch torchvision
- install all dependencies by running the following command:
pip install -r requirements.txt
Getting started
-
eval.py
demonstrates the results on the HPatches dataset To be able to runeval.py
script:- Download an archive with pre-trained models click and extract it to the project folder
- Download HPatches dataset (Full image sequences). The dataset is available here at the end of the page
- Run the following command:
python eval.py --image-data-path /path/to/hpatches-geometry
-
train.py
is a script to train DGC-Net/DGCM-Net model from scratch. To run this script, please follow the next procedure:- Download the TokyoTimeMachine dataset
- Run the command:
python train.py --image-data-path /path/to/TokyoTimeMachine
Performance on HPatches dataset
Method / HPatches ID Viewpoint 1 Viewpoint 2 Viewpoint 3 Viewpoint 4 Viewpoint 5 PWC-Net 4.43 11.44 15.47 20.17 28.30 GM best model 9.59 18.55 21.15 27.83 35.19 DGC-Net (paper) 1.55 5.53 8.98 11.66 16.70 DGCM-Net (paper) 2.97 6.85 9.95 12.87 19.13 DGC-Net (repo) 1.74 5.88 9.07 12.14 16.50 DGCM-Net (repo) 2.33 5.62 9.55 11.59 16.48Note: There is a difference in numbers presented in the original paper and obtained by the models of this repo. It might be related to the fact that both models (DGC-Net and DGCM-Net) have been trained using Pytorch v0.3
.
More qualitative results are presented on the project page
How to cite
If you use this software in your own research, please cite our publication:
@inproceedings{Melekhov+Tiulpin+Sattler+Pollefeys+Rahtu+Kannala:2018,
title = {{DGC-Net}: Dense geometric correspondence network},
author = {Melekhov, Iaroslav and Tiulpin, Aleksei and
Sattler, Torsten, and
Pollefeys, Marc and
Rahtu, Esa and Kannala, Juho},
year = {2019},
booktitle = {Proceedings of the IEEE Winter Conference on
Applications of Computer Vision (WACV)}
}
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK