liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
HDR image reconstruction from a single exposure using deep CNNs
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-9217-9997
Linköping University, Department of Science and Technology. Linköping University, Faculty of Science & Engineering.
University of Cambridge, England.
University of Cambridge, England.
Show others and affiliations
2017 (English)In: ACM Transactions on Graphics, ISSN 0730-0301, E-ISSN 1557-7368, Vol. 36, no 6, article id 178Article in journal (Refereed) Published
Abstract [en]

Camera sensors can only capture a limited range of luminance simultaneously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting information that have been lost in saturated image areas, in order to enable HDR reconstruction from a single exposure. We show that this problem is well-suited for deep learning algorithms, and propose a deep convolutional neural network (CNN) that is specifically designed taking into account the challenges in predicting HDR values. To train the CNN we gather a large dataset of HDR images, which we augment by simulating sensor saturation for a range of cameras. To further boost robustness, we pre-train the CNN on a simulated HDR dataset created from a subset of the MIT Places database. We demonstrate that our approach can reconstruct high-resolution visually convincing HDR results in a wide range of situations, and that it generalizes well to reconstruction of images captured with arbitrary and low-end cameras that use unknown camera response functions and post-processing. Furthermore, we compare to existing methods for HDR expansion, and show high quality results also for image based lighting. Finally, we evaluate the results in a subjective experiment performed on an HDR display. This shows that the reconstructed HDR images are visually convincing, with large improvements as compared to existing methods.

Place, publisher, year, edition, pages
ASSOC COMPUTING MACHINERY , 2017. Vol. 36, no 6, article id 178
Keywords [en]
HDR reconstruction; inverse tone-mapping; deep learning; convolutional network
National Category
Media Engineering
Identifiers
URN: urn:nbn:se:liu:diva-143943DOI: 10.1145/3130800.3130816ISI: 000417448700008OAI: oai:DiVA.org:liu-143943DiVA, id: diva2:1169758
Conference
10th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia
Note

Funding Agencies|Linkoping University Center for Industrial Information Technology (CENIIT); Swedish Science Council [2015-05180]; Wallenberg Autonomous Systems Program (WASP)

Available from: 2017-12-29 Created: 2017-12-29 Last updated: 2023-04-03
In thesis
1. The high dynamic range imaging pipeline: Tone-mapping, distribution, and single-exposure reconstruction
Open this publication in new window or tab >>The high dynamic range imaging pipeline: Tone-mapping, distribution, and single-exposure reconstruction
2018 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Techniques for high dynamic range (HDR) imaging make it possible to capture and store an increased range of luminances and colors as compared to what can be achieved with a conventional camera. This high amount of image information can be used in a wide range of applications, such as HDR displays, image-based lighting, tone-mapping, computer vision, and post-processing operations. HDR imaging has been an important concept in research and development for many years. Within the last couple of years it has also reached the consumer market, e.g. with TV displays that are capable of reproducing an increased dynamic range and peak luminance.

This thesis presents a set of technical contributions within the field of HDR imaging. First, the area of HDR video tone-mapping is thoroughly reviewed, evaluated and developed upon. A subjective comparison experiment of existing methods is performed, followed by the development of novel techniques that overcome many of the problems evidenced by the evaluation. Second, a largescale objective comparison is presented, which evaluates existing techniques that are involved in HDR video distribution. From the results, a first open-source HDR video codec solution, Luma HDRv, is built using the best performing techniques. Third, a machine learning method is proposed for the purpose of reconstructing an HDR image from one single-exposure low dynamic range (LDR) image. The method is trained on a large set of HDR images, using recent advances in deep learning, and the results increase the quality and performance significantly as compared to existing algorithms.

The areas for which contributions are presented can be closely inter-linked in the HDR imaging pipeline. Here, the thesis work helps in promoting efficient and high-quality HDR video distribution and display, as well as robust HDR image reconstruction from a single conventional LDR image.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2018. p. 132
Series
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 1939
Keywords
high dynamic range imaging, tone-mapping, video tone-mapping, HDR video encoding, HDR image reconstruction, inverse tone-mapping, machine learning, deep learning
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-147843 (URN)10.3384/diss.diva-147843 (DOI)9789176853023 (ISBN)
Public defence
2018-06-08, Domteatern, Visualiseringscenter C, Kungsgatan 54, Campus Norrköping, Norrköping, 09:15 (English)
Opponent
Supervisors
Available from: 2018-05-15 Created: 2018-05-15 Last updated: 2023-04-03Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Eilertsen, GabrielKronander, JoelUnger, Jonas
By organisation
Media and Information TechnologyFaculty of Science & EngineeringDepartment of Science and Technology
In the same journal
ACM Transactions on Graphics
Media Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 612 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf