Deep joint demosaicking and denoising
Name
demosaic.pdf
Description
Accepted version
Size
55.92 MB
Format
Adobe PDF
Checksum (MD5)
4e3d15407847c397530e74319fea9376
Author(s)
Gharbi, Michaël
Chaurasia, Gaurav
Paris, Sylvain
Durand, Frédo
Date Issued
2016
Journal
ACM Transactions on Graphics
Publisher
Association for Computing Machinery (ACM)
Citation
Gharbi, Michael, et al. "Deep Joint Demosaicking and Denoising." Acm Transactions on Graphics 35 6 (2016): 12.
Version
Author's final manuscript
Abstract
© 2016 ACM. SA'16 Technical Papers,, December 05-08, 2016, Macao Demosaicking and denoising are the key first stages of the digital imaging pipeline but they are also a severely ill-posed problem that infers three color values per pixel from a single noisy measurement. Earlier methods rely on hand-crafted filters or priors and still exhibit disturbing visual artifacts in hard cases such as moiré or thin edges. We introduce a new data-driven approach for these challenges: we train a deep neural network on a large corpus of images instead of using hand-tuned filters. While deep learning has shown great success, its naive application using existing training datasets does not give satisfactory results for our problem because these datasets lack hard cases. To create a better training set, we present metrics to identify difficult patches and techniques for mining community photographs for such patches. Our experiments show that this network and training procedure outperform state-of-the-art both on noisy and noise-free data. Furthermore, our algorithm is an order of magnitude faster than the previous best performing techniques.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/2980179.2982399
