Deep Learning for HDR Imaging: State-of-the-Art and Future Trends

Cited 25 time in webofscience Cited 0 time in scopus
  • Hit : 250
  • Download : 0
High dynamic range (HDR) imaging is a technique to allow a greater dynamic range of exposures, which is a very important field in image processing, computer graphics, and vision. Recent years have witnessed a striking advancement of HDR imaging using deep learning. This paper aims to provide a systematic review and analysis of the recent development of deep HDR imaging methodologies. Overall, we hierarchically and structurally group existing deep HDR imaging methods into five categories based on the number/domain of input exposures in HDR imaging, the number of learning tasks in HDR imaging, HDR imaging using the novel sensor data, HDR imaging using novel learning strategies, and the applications. Importantly, we provide constructive discussions for each category regarding its potential and challenges. Moreover, we cover some crucial issues for deep HDR imaging, such as datasets and evaluation metrics. Lastly, we highlight some open issues and point out future directions by sharing some new perspectives.
Publisher
IEEE COMPUTER SOC
Issue Date
2022-12
Language
English
Article Type
Article
Citation

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.44, no.12, pp.8874 - 8895

ISSN
0162-8828
DOI
10.1109/TPAMI.2021.3123686
URI
http://hdl.handle.net/10203/301139
Appears in Collection
ME-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 25 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0