Home

Awesome

A Comparative Study for Single Image Blind Deblurring (CVPR 2016)

Introduction

This is the research code for the paper:

Wei-Sheng Lai, Jia-Bin Huang, Zhe Hu, [Narendra Ahuja] (http://vision.ai.illinois.edu/ahuja.html), and Ming-Hsuan Yang, "A Comparative Study for Single Image Blind Deblurring", IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

Project webpage

Paper

Citation

If you find the code and datasets useful in your research, please cite:

@inproceedings{Lai-CVPR-2016,
    author    = {Lai, Wei-Sheng and Huang, Jia-Bin and Hu, Zhe and Ahuja, Narendra and Yang, Ming-Hsuan}, 
    title     = {A Comparative Study for Single Image Blind Deblurring}, 
    booktitle = {IEEE Conferene on Computer Vision and Pattern Recognition},
    year      = {2016}
}

Contents

Folder/FilesDescription
attributes/lists of image id for each attribute
list/lists of image names for our datasets
votes/user voting results
*.mMATLAB code
BT_scores.pdfA slide described the algorithm and implementation details of the BT scores

Our code is implemented and tested on Windows 7 / Ubuntu 14.04 with MATLAB R2015a.

Run demo_bt_ranking.m, demo_dataset_correlation.m, demo_kendall.m, and demo_significance_test.m to reproduce the analysis in our paper.

Our datasets could be downloaded from the project webpage.