Deep joint demosaicking and denoising
© 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 h...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Association for Computing Machinery (ACM)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/134672 |
| _version_ | 1826194003195854848 |
|---|---|
| author | Gharbi, Michaël Chaurasia, Gaurav Paris, Sylvain Durand, Frédo |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Gharbi, Michaël Chaurasia, Gaurav Paris, Sylvain Durand, Frédo |
| author_sort | Gharbi, Michaël |
| collection | MIT |
| description | © 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. |
| first_indexed | 2024-09-23T09:49:02Z |
| format | Article |
| id | mit-1721.1/134672 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T09:49:02Z |
| publishDate | 2021 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/1346722023-02-24T21:34:41Z Deep joint demosaicking and denoising Gharbi, Michaël Chaurasia, Gaurav Paris, Sylvain Durand, Frédo Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © 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. 2021-10-27T20:06:07Z 2021-10-27T20:06:07Z 2016 2019-05-29T12:54:09Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/134672 Gharbi, Michael, et al. "Deep Joint Demosaicking and Denoising." Acm Transactions on Graphics 35 6 (2016): 12. en 10.1145/2980179.2982399 ACM Transactions on Graphics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery (ACM) MIT web domain |
| spellingShingle | Gharbi, Michaël Chaurasia, Gaurav Paris, Sylvain Durand, Frédo Deep joint demosaicking and denoising |
| title | Deep joint demosaicking and denoising |
| title_full | Deep joint demosaicking and denoising |
| title_fullStr | Deep joint demosaicking and denoising |
| title_full_unstemmed | Deep joint demosaicking and denoising |
| title_short | Deep joint demosaicking and denoising |
| title_sort | deep joint demosaicking and denoising |
| url | https://hdl.handle.net/1721.1/134672 |
| work_keys_str_mv | AT gharbimichael deepjointdemosaickinganddenoising AT chaurasiagaurav deepjointdemosaickinganddenoising AT parissylvain deepjointdemosaickinganddenoising AT durandfredo deepjointdemosaickinganddenoising |