@inproceedings{20fcc0d1e91e4e6bb3a3e2f6046b59ed,
title = "Depth estimation and blur removal from a single out-of-focus image",
abstract = "This paper presents a depth estimation method that leverages rich representations learned from cascaded convolutional and fully connected neural networks operating on a patch-pooled set of feature maps. Our method is very fast and it substantially improves depth accuracy over the state-of-the-art alternatives, and from this, we computationally reconstruct an all-focus image and achieve synthetic re-focusing, all from a single image. Our experiments on benchmark datasets such as Make3D and NYU-v2 demonstrate superior performance in comparison to other available depth estimation methods by reducing the root-mean-squared error by 57\% \& 46\%, and blur removal methods by 0.36 dB \& 0.72 dB in PSNR, respectively. This improvement is also demonstrated by the superior performance using real defocus images.",
author = "Saeed Anwar and Zeeshan Hayder and Fatih Porikli",
note = "Publisher Copyright: {\textcopyright} 2017. The copyright of this document resides with its authors.; 28th British Machine Vision Conference, BMVC 2017 ; Conference date: 04-09-2017 Through 07-09-2017",
year = "2017",
doi = "10.5244/c.31.113",
language = "English",
series = "British Machine Vision Conference 2017, BMVC 2017",
publisher = "BMVA Press",
booktitle = "British Machine Vision Conference 2017, BMVC 2017",
}