Learning a Deep Convolutional Network for Light-Field Image Super-Resolution
Abstract
Commercial Light-Field cameras provide spatial and angular information, but its limited resolution becomes an important problem in practical use. In this paper, we present a novel method for Light-Field image super-resolution (SR) via a deep convolutional neural network. Rather than the conventional optimization framework, we adopt a datadriven learning method to simultaneously up-sample the angular resolution as well as the spatial resolution of a Light-Field image. We first augment the spatial resolution of each sub-aperture image to enhance details by a spatial SR network. Then, novel views between the sub-aperture images are generated by an angular super-resolution network. These networks are trained independently but finally finetuned via end-to-end training. The proposed method shows the state-of-the-art performance on HCI synthetic dataset, and is further evaluated by challenging real-world applications including refocusing and depth map estimation.
Cite
Text
Yoon et al. "Learning a Deep Convolutional Network for Light-Field Image Super-Resolution." IEEE/CVF International Conference on Computer Vision Workshops, 2015. doi:10.1109/ICCVW.2015.17Markdown
[Yoon et al. "Learning a Deep Convolutional Network for Light-Field Image Super-Resolution." IEEE/CVF International Conference on Computer Vision Workshops, 2015.](https://mlanthology.org/iccvw/2015/yoon2015iccvw-learning/) doi:10.1109/ICCVW.2015.17BibTeX
@inproceedings{yoon2015iccvw-learning,
title = {{Learning a Deep Convolutional Network for Light-Field Image Super-Resolution}},
author = {Yoon, Youngjin and Jeon, Hae-Gon and Yoo, Donggeun and Lee, Joon-Young and Kweon, In So},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2015},
pages = {57-65},
doi = {10.1109/ICCVW.2015.17},
url = {https://mlanthology.org/iccvw/2015/yoon2015iccvw-learning/}
}