ML Anthology

Learning to Autofocus

Charles Herrmann, Richard Strong Bowen, Neal Wadhwa, Rahul Garg, Qiurui He, Jonathan T. Barron, Ramin Zabih
CVPR 2020
doi:10.1109/CVPR42600.2020.00230 /cvpr/2020/herrmann2020cvpr-learning/

Abstract

Autofocus is an important task for digital cameras, yet current approaches often exhibit poor performance. We propose a learning-based approach to this problem, and provide a realistic dataset of sufficient size for effective learning. Our dataset is labeled with per-pixel depths obtained from multi-view stereo, following [9]. Using this dataset, we apply modern deep classification models and an ordinal regression loss to obtain an efficient learning-based autofocus technique. We demonstrate that our approach provides a significant improvement compared with previous learned and non-learned methods: our model reduces the mean absolute error by a factor of 3.6 over the best comparable baseline algorithm. Our dataset and code are publicly available.

PDF CVPR Semantic Scholar

Cite

Text

Herrmann et al. "Learning to Autofocus." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00230

Markdown

[Herrmann et al. "Learning to Autofocus." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/herrmann2020cvpr-learning/) doi:10.1109/CVPR42600.2020.00230

BibTeX

@inproceedings{herrmann2020cvpr-learning,
  title     = {{Learning to Autofocus}},
  author    = {Herrmann, Charles and Bowen, Richard Strong and Wadhwa, Neal and Garg, Rahul and He, Qiurui and Barron, Jonathan T. and Zabih, Ramin},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00230},
  url       = {https://mlanthology.org/cvpr/2020/herrmann2020cvpr-learning/}
}