HiFST

<p align="center"> <b>Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes </b><br> S. Alireza Golestaneh, and Lina J. Karam<br> <b> IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul 2017</b> </p> <p align="center"> <img src="https://cloud.githubusercontent.com/assets/12434910/26278354/59f5d0e4-3d4d-11e7-8452-43436c41c478.jpg"> </p>

In this work, we propose a novel effective approach to address the blur detection problem from a single image without requiring any knowledge about the blur type, level, or camera settings. Our approach computes blur detection maps based on a novel High-frequency multiscale Fusion and Sort Transform (HiFST) of gradient magnitudes.

@inproceedings{golestaneh2017spatially,
  title={Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes},
  author={Golestaneh, S Alireza and Karam, Lina J},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  year={2017}
}