HDR image reconstruction from a single exposure using deep CNNs
- Submitting institution
-
University of Cambridge
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 8990
- Type
- D - Journal article
- DOI
-
10.1145/3130800.3130816
- Title of journal
- ACM Transactions on Graphics
- Article number
- ARTN 178
- First page
- 6
- Volume
- 36
- Issue
- 6
- ISSN
- 0730-0301
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 109
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work has attracted much attention as it is one of the first methods that can produce a high-quality reconstruction of saturated pixels. It allows using longer exposure times (and hence less noise) in very popular burst-image capture used in most mobile phone cameras. The talk on this work was invited to Future ISP technologies workshop in Sophia Antipolis (sponsored by Huawei). This project also attracted Huawei-sponsored PhD studentship in Cambridge.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -