Perceptually Motivated Loss Functions for Computer Generated Holographic Displays
View / Open Files
Authors
Kadis, Andrew
Yang, Fan
Mouthaan, Ralf
Wetherfield, Benjamin
Kaczorowski, Andrzej
Publication Date
2022-05-11Journal Title
Scientific Reports
ISSN
2045-2322
Publisher
Nature Publishing Group
Type
Article
Metadata
Show full item recordCitation
Wilkinson, T., Kadis, A., Yang, F., Mouthaan, R., Wetherfield, B., & Kaczorowski, A. (2022). Perceptually Motivated Loss Functions for Computer Generated Holographic Displays. Scientific Reports https://doi.org/10.1038/s41598-022-11373-8
Abstract
Understanding and improving the perceived quality of reconstructed images is key to developing computer-generated holography algorithms for high-fidelity holographic displays. However, current algorithms are typically optimized using mean squared error, which is widely criticized for its poor correlation with perceptual quality. In our work, we present a comprehensive analysis of employing contemporary image quality metrics (IQM) as loss-functions in the hologram optimization process. Extensive objective and subjective assessment of experimentally reconstructed images reveal the relative performance of IQM losses for hologram optimization. Our results reveal that the perceived image quality improves considerably when the appropriate IQM loss function is used, highlighting the value of developing perceptually-motivated loss functions for hologram optimization.
Sponsorship
Engineering and Physical Sciences Research Council (EP/P030181/1)
The Cambridge Trust as well as The China Scholarship Council
Department of Engineering, University of Cambridge (Richard Norman Scholarship)
Funder references
EPSRC (EP/T008369/1)
EPSRC (2108797)
Identifiers
External DOI: https://doi.org/10.1038/s41598-022-11373-8
This record's URL: https://www.repository.cam.ac.uk/handle/1810/337472
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.