Fig. 1. OSH system setup^[28]. BS1 and BS2, beam splitter; M1 and M2, mirror; AOFS, acousto-optic frequency shifter; p₁ (x, y) and p₂ (x, y), pupils; L1, L2, and L3, lens; PD, photo detector; BPF, band-pass filter.

Fig. 2. The architecture of U-net. ‘Conv, 3 × 3’ represents a 3 × 3 convolution kernel with the ReLU activation function. ‘Padding=same’ means that the matrix dimensions of the input and output in the convolution layer are the same. ‘Maxpool 2 × 2’ represents the function to choose the maximum value from a 2 × 2 matrix. ‘Upsampling and conv, 2 × 2’ stands for upsampling using a 2 × 2 convolution kernel. Each blue box represents a multi-channel feature map, while the white ones represent the copied feature maps.

Fig. 3. Input images for the U-net model.

Fig. 4. Standard images of the U-net model.

Fig. 5. The relationship between the loss function and iteration times.

Fig. 6. The reconstruction results with U-net. (a), (d), and (g) are the original images. (b), (e), and (h) are input images with speckle-like noise generated by different random phase pupils. (c), (f), and (i) are the corresponding reconstructed output images.

Fig. 7. Sectioning results with different noise ratios based on the U-net method.

Fig. 8. The original images for generating the training data sets.

Fig. 9. The relationship between the loss function and iteration times in the complex graphics.

Fig. 10. The test results of the complex graphics with U-net. (a),(d) are the original images of ‘Monkey’ and ‘Rice’. (b),(e) are the input images with speckle-like noise generated by different random phase pupils. (c),(f) are the corresponding output images of the U-net.

Fig. 11. (a) Object with two slices, and (b) the recorded hologram.

Fig. 12. (a) , (b) Sectional results of the conventional method. (c) , (d) Sectional results of the proposed U-net method, with z₁ = 9 mm and z₂ = 10 mm.

Fig. 13. The 3D rocket.

Fig. 14. (a)–(f) Sectional images of the 3D rocket. (g)–(l) Reconstructed images with the traditional method. (m)–(r) Reconstructed images with the proposed method.

Fig. 15. PSNR of the sectioning results.

Fig. 16. SSIM of the sectioning results.