“Distance-adaptive unsupervised CNN model for computer-generated holography” by Asano, Yamamoto, Fushimi and Ochiai
Conference:
Type(s):
Title:
- Distance-adaptive unsupervised CNN model for computer-generated holography
Session/Category Title: Rendering & Displays
Presenter(s)/Author(s):
Abstract:
We propose a CNN model for CGH synthesis that allows specifying not only target image but also propagation distance. Our model demonstrates comparable performance to traditional fixed-distance methods and achieves practical generation accuracy and speed even when the propagation distance is changed, enabling CGH generation in various contexts.
References:
[1]
Eirikur Agustsson and Radu Timofte. 2017. NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.
[2]
Joseph W. Goodman. 2005. Introduction to Fourier optics (3rd ed. ed.). Roberts, Englewood.
[3]
Andrew Maimone, Andreas Georgiou, and Joel S. Kollin. 2017. Holographic Near-Eye Displays for Virtual and Augmented Reality. ACM Trans. Graph. 36, 4, Article 85 (jul 2017), 16 pages. https://doi.org/10.1145/3072959.3073624
[4]
Yifan Peng, Suyeon Choi, Nitish Padmanaban, and Gordon Wetzstein. 2020. Neural Holography with Camera-in-the-Loop Training. ACM Trans. Graph. 39, 6, Article 185 (nov 2020), 14 pages. https://doi.org/10.1145/3414685.3417802
