The High Dynamic Range Imaging Pipeline : : Tone-Mapping, Distribution, and Single-exposure Reconstruction.

• Superior document: Linköping Studies in Science and Technology. Dissertations Series ; v.1939
• Author: Eilertsen, Gabriel.
• Place / Publishing House: Linköping : : Linkopings Universitet,, 2018.; {copy}2018.
• Year of Publication: 2018
• Edition: 1st ed.
• Language: English
• Series: Linköping Studies in Science and Technology. Dissertations Series
• Physical Description: 1 online resource (154 pages)

Table of Contents

Intro -- Abstract -- Populärvetenskaplig sammanfattning -- Acknowledgments -- Publications -- Contributions -- Contents -- 1 Introduction -- 1.1 High dynamic range -- 1.1.1 Definition -- 1.1.2 The dynamic range of the HVS -- 1.1.3 Camera and display dynamic range -- 1.1.4 Calibration -- 1.1.5 Applications -- 1.2 Context -- 1.3 Author's contributions -- 1.4 Disposition -- 2 Background -- 2.1 Capturing with HDR cameras -- 2.1.1 Single-exposure HDR cameras -- 2.1.2 Multi-exposure HDR camera systems -- 2.2 HDR reconstruction from conventional sensors -- 2.2.1 Temporally multiplexed exposures -- 2.2.2 Spatially multiplexed exposures -- 2.2.3 Single-exposure techniques -- 2.3 HDR distribution -- 2.3.1 Floating point HDR pixel formats -- 2.3.2 HDR encoding using LDR formats -- 2.4 Tone-mapping -- 2.4.1 Categorization -- 2.4.2 Tone-mapping pipeline -- 2.4.4 Evaluation -- 2.5 HDR displays -- 2.5.1 Professional HDR display devices -- 2.5.2 HDR TVs -- 3 Tone-mapping of HDR video -- 3.1 Motivation -- 3.2 Evaluation of TMOs -- 3.2.1 Parameter calibration -- 3.2.2 Qualitative evaluation experiment -- 3.2.3 Pair-wise comparison experiment -- 3.3 New algorithms -- 3.3.1 Filtering for tone-mapping -- 3.3.2 Tone-curve -- 3.3.3 Noise-awareness -- 3.4 Recent developments -- 3.5 Summary -- 4 Distribution of HDR video -- 4.1 Motivation -- 4.2 Evaluation -- 4.2.1 Setup -- 4.2.2 Results -- 4.2.3 Comparison to HDR10 -- 4.4 Summary -- 4.4.1 Limitations and future work -- 5 Single-exposure HDR image reconstruction -- 5.1 Motivation -- 5.1.1 Relation to inverse tone-mapping -- 5.1.2 Where is the dynamic range? -- 5.2 Deep learning for HDR imaging -- 5.3 Deep learning reconstruction -- 5.3.1 CNN design -- 5.3.2 Training -- 5.3.3 Weight initialization -- 5.3.4 Results -- 5.3.5 Compression artifacts -- 5.3.6 Adversarial training -- 5.4 Summary.

5.4.1 Limitations and future work -- 6 Conclusions -- 6.1 Contributions -- 6.1.1 Tone-mapping -- 6.1.2 Distribution -- 6.1.3 Reconstruction -- 6.2 Outlook -- Bibliography -- Publications.