Add to BibSonomyAbstract
Image quality assessment metrics do not reliably represent human perception of computer-generated holograms, limiting the performance of holographic displays. We developed a neural network with semi-supervised training that accurately predicts how viewers perceive hologram quality.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Self-supervised neural network for holographic microscopy
Luzhe Huang, Hanlong Chen, Tairan Liu, and Aydogan Ozcan
ATu3Q.4 CLEO: Applications and Technology (CLEO:A&T) 2023
High-Quality Hologram Generation Based on Advanced Layering Approach and Deep Neural Network for Holographic Display
Tuvshinjargal Amgalan, Erkhembaatar Dashdavaa, F M Fahmid Hossain, Rupali Shinde, Md. Biddut Hossain, Hui-Ying Wu, Seok-Hee Jeon, and Nam-Kim
JTu4A.30 3D Image Acquisition and Display: Technology, Perception and Applications (3D) 2023
Deep neural network and its training strategy for converting computer-generated hologram between different display systems
Juhyun Lee and Byoungho Lee
W2A.11 Digital Holography and Three-Dimensional Imaging (DH) 2022