Abstract

We propose a reconstruction method for coherence holography using deep neural networks. cGAN and U-NET models were developed to reconstruct 3D complex objects from recorded interferograms. Our proposed methods, dubbed deep coherence holography (DCH), predict the non-diffracted fields or the sub-objects included in the 3D object from the captured interferograms, yielding better reconstructed objects than the traditional analytical imaging methods in terms of accuracy, resolution, and time. The DCH needs one image per sub-object as opposed to $N$ images for the traditional sin-fit algorithm, and hence the total reconstruction time is reduced by $N \times$. Furthermore, with noisy interferograms the DCH amplitude mean square reconstruction error (MSE) is $5 \times 10^4 \times $ and $10^4 \times$ and phase MSE is ${10}^{2}\times$ and $3 \times 10^3 \times$ better than Fourier fringe and sin-fit algorithms, respectively. The amplitude peak signal to noise ratio (PSNR) is $3 \times$ and $2 \times$ and phase PSNR is $5 \times$ and $3 \times$ better than Fourier fringe and sin-fit algorithms, respectively. The reconstruction resolution is the same as sin-fit but $2 \times$ better than the Fourier fringe analysis technique.

© 2023 Optica Publishing Group

Single-shot Fresnel incoherent correlation holography via deep learning based phase-shifting technology

Tao Huang, Qinnan Zhang, Jiaosheng Li, Xiaoxu Lu, Jianglei Di, Liyun Zhong, and Yuwen Qin
Opt. Express 31(8) 12349-12356 (2023)

LiteF2DNet: a lightweight learning framework for 3D reconstruction using fringe projection profilometry

Vaishnavi Ravi and Rama Krishna Gorthi
Appl. Opt. 62(12) 3215-3224 (2023)

Single-shot 3D measurement of highly reflective objects with deep learning

MingZhu Wan and Lingbao Kong
Opt. Express 31(9) 14965-14985 (2023)

Digital holography without a dark room environment: extraction of interference fringes by using deep learning

Yuki Nagahama
Appl. Opt. 62(33) 8911-8917 (2023)

Coherence holography by achromatic 3-D field correlation of generic thermal light with an imaging Sagnac shearing interferometer

Dinesh N. Naik, Takahiro Ezawa, Rakesh Kumar Singh, Yoko Miyamoto, and Mitsuo Takeda
Opt. Express 20(18) 19658-19669 (2012)