SimFIR

The official code for “SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning”, ICCV, 2023.

🚀 Demo (Link)

1. Upload the distorted document image to be rectified in the left box.
2. Click the "Submit" button.
3. The rectified image will be displayed in the right box.

Dataset

This repository contains the dataset organized into two main directories:

• images: Contains distorted image files.
• flow: Stores the warping flow files.

Each of these directories further comprises two sub-directories:

• train: For training data.
• test: For testing data.

Click here to access the dataset.

Inference

1. Put the pre-trained model to $ROOT/model_pretrained/.
2. Put the distorted images in $ROOT/distorted/.
3. Run the script and the rectified images are saved in $ROOT/rectified/ by default.

   python inference.py
   

Citation

If you find this code useful for your research, please use the following BibTeX entry.

@inproceedings{feng2023simfir,
  title={Simfir: A simple framework for fisheye image rectification with self-supervised representation learning},
  author={Feng, Hao and Wang, Wendi and Deng, Jiajun and Zhou, Wengang and Li, Li and Li, Houqiang},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={12418--12427},
  year={2023}
}