https://github.com/xiaoyu258/GeoProj

Blind Geometric Distortion Correction on Images Through Deep Learning
https://github.com/xiaoyu258/GeoProj

deep-learning distortion-correction pytorch

Last synced: 3 months ago
JSON representation

Blind Geometric Distortion Correction on Images Through Deep Learning

• Host: GitHub
• URL: https://github.com/xiaoyu258/GeoProj
• Owner: xiaoyu258
• License: mit
• Created: 2019-08-28T12:11:11.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2022-09-28T08:15:08.000Z (over 1 year ago)
• Last Synced: 2024-02-20T05:38:19.781Z (4 months ago)
• Topics: deep-learning, distortion-correction, pytorch
• Language: Python
• Homepage:
• Size: 821 KB
• Stars: 154
• Watchers: 6
• Forks: 46
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-lists - Blind Geometric Distortion Correction on Images Through Deep Learning

README

        
# GeoProj

### [Paper](https://arxiv.org/abs/1909.03459)

The source code of Blind Geometric Distortion Correction on Images Through Deep Learning by Li et al, CVPR 2019. 

 

## Prerequisites

- Linux or Windows

- Python 3

- CPU or NVIDIA GPU + CUDA CuDNN

## Getting Started

### Dataset Generation

In order to train the model using the provided code, the data needs to be generated in a certain manner. 

You can use any distortion-free images to generate the dataset. In this paper, we use [Places365-Standard dataset](http://places2.csail.mit.edu/download.html) at the resolution of 512\*512 as the original non-distorted images to generate the 256\*256 dataset.

Run the following command for dataset generation:

```bash

python data/dataset_generate.py [--sourcedir [PATH]] [--datasetdir [PATH]] 

                                [--trainnum [NUMBER]] [--testnum [NUMBER]]

--sourcedir           Path to original non-distorted images

--datasetdir          Path to the generated dataset

--trainnum            Number of generated training samples

--testnum             Number of generated testing samples

```

### Training

Run the following command for help message about optional arguments like learning rate, dataset directory, etc.

```bash

python trainNetS.py --h # if you want to train GeoNetS

python trainNetM.py --h # if you want to train GeoNetM

```

### Use a Pre-trained Model

You can download the pretrained model [here](https://drive.google.com/open?id=1Tdi92IMA-rrX2ozdUMvfiN0jCZY7wIp_).

You can also use `eval.py` and modify the model path, image path and saved result path to your own directory to generate your own results.

### Resampling

Import `resample.resampling.rectification` function to resample the distorted image by the forward flow.

The distorted image should be a Numpy array with the shape of H\*W\*3 for a color image or H\*W for a greyscale image, the forward flow should be an array with the shape of 2\*H\*W.

The function will return the resulting image and a mask to indicate whether each pixel will converge within the maximum iteration.

## Citation

```bash

@inproceedings{li2019blind,

  title={Blind Geometric Distortion Correction on Images Through Deep Learning},

  author={Li, Xiaoyu and Zhang, Bo and Sander, Pedro V and Liao, Jing},

  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},

  pages={4855--4864},

  year={2019}

}

```