Defocus Magnification Using Conditional Adversarial Networks
Abstract
Defocus magnification is the process of rendering a shallow depth-of-field in an image captured using a camera with a narrow aperture. Defocus magnification is a useful tool in photography for emphasis on the subject and for highlighting background bokeh. Estimating the per-pixel blur kernel or the depth-map of the scene followed by spatially-varying re-blurring is the standard approach to defocus magnification. We propose a single-step approach that directly converts a narrow-aperture image to a wide-aperture image. We use a conditional adversarial network trained on multi-aperture images created from light-fields. We use a novel loss term based on a composite focus measure to improve generalization and show high quality defocus magnification.
Cite
Text
Sakurikar et al. "Defocus Magnification Using Conditional Adversarial Networks." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019. doi:10.1109/WACV.2019.00147Markdown
[Sakurikar et al. "Defocus Magnification Using Conditional Adversarial Networks." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019.](https://mlanthology.org/wacv/2019/sakurikar2019wacv-defocus/) doi:10.1109/WACV.2019.00147BibTeX
@inproceedings{sakurikar2019wacv-defocus,
title = {{Defocus Magnification Using Conditional Adversarial Networks}},
author = {Sakurikar, Parikshit and Mehta, Ishit and Narayanan, P. J.},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2019},
pages = {1337-1346},
doi = {10.1109/WACV.2019.00147},
url = {https://mlanthology.org/wacv/2019/sakurikar2019wacv-defocus/}
}