Abstract

Autostereoscopic 3D measuring systems are an accurate, rapid, and portable method for in situ measurements. These systems use a micro-lens array to record 3D information based on the light-field theory. However, the spatial-angular-resolution trade-off curtails their performance. Although learning models were developed for super-resolution, the scarcity of data hinders efficient training. To address this issue, a novel, to the best of our knowledge, semi-supervised learning paradigm for angular super-resolution is proposed for data-efficient training, benefiting both autostereoscopic and light-field devices. A convolutional neural network using motion estimation is developed for a view synthesis. Subsequently, a high-angular-resolution autostereoscopic system is presented for an accurate profile reconstruction. Experiments show that the semi-supervision enhances view reconstruction quality, while the amount of training data required is reduced by over 69%.

© 2024 Optica Publishing Group

Physics-based supervised learning method for high dynamic range 3D measurement with high fidelity

Fuqian Li, Xingman Niu, Jing Zhang, Qican Zhang, and Yajun Wang
Opt. Lett. 49(3) 602-605 (2024)

Self super-resolution autostereoscopic 3D measuring system using deep convolutional neural networks

Sanshan Gao, Chi Fai Cheung, and Da Li
Opt. Express 30(10) 16313-16329 (2022)

Global-optimal semi-supervised learning for single-pixel image-free sensing

Xinrui Zhan, Hui Lu, Rong Yan, and Liheng Bian
Opt. Lett. 49(3) 682-685 (2024)

Disparity pattern-based autostereoscopic 3D metrology system for in situ measurement of microstructured surfaces

Da Li, Chi Fai Cheung, MingJun Ren, David Whitehouse, and Xing Zhao
Opt. Lett. 40(22) 5271-5274 (2015)

Data-driven method of super-resolution image recovery for speckle-illumination photoacoustic computed tomography

Tianhua Zhou, Boyi Li, Xin Liu, and Dean Ta
Opt. Lett. 49(8) 1949-1952 (2024)