Fig. 1. Schematic of our metalens imaging system.

Fig. 2. (a) Photograph of fabricated mass-produced 10-mm-diameter metalenses on 4″ glass wafer. The inset in the red box shows enlarged image of the metalens. (b) Scanning electron microscopy (SEM) image showing the meta-atoms that compose the metalens. The scale bar is 3μm. (c) Focal lengths of the metalens for wavelengths of 450 nm (blue), 532 nm (green), and 635 nm (red). The dashed line indicates the linear fitting result. (d) MTFs of red, green, and blue lights with zero viewing angle. (e) PSFs of red, green, and blue lights with various viewing angles (0 deg, 5 deg, 10 deg). The scale bar is 1 mm, which indicates a distance on the image sensor. (f) Metalens image (left) and its subset images showing red, green, and blue color channels. (g) Corresponding ground truth image (left) and its subset images showing red, green, and blue color channels.

Fig. 3. Proposed image restoration framework. The framework consists of an image restoration model and applies random cropping and position embedding to the input data using coordinate information of the cropped patches. To address the underconstrained problem of restoring degraded images to latent sharp images, adversarial learning in the frequency domain is applied through the FFT (F). x^ and x denote the reconstructed and ground truth image, respectively. The details of the framework are in Sec. 2.

Fig. 4. (a) Ground truth images, (b) metalens images, and (c) images reconstructed by our model. The images are affiliated with the test set data. The central (red) and outer (yellow) regions of the images are enlarged to access the restoration of the metalens image at high and low viewing angle, respectively. The outer regions of the metalens images (yellow box) are successfully restored, even though those are more severely degraded than the inner region (red box) due to the angular aberration under high viewing angle.

Fig. 5. Comparative statistical analysis of the proposed model and metalens imaging results using the test dataset. (a)–(e) Results of PSNR, SSIM, LPIPS in RGB space and CS, MAE of the magnitudes in Fourier space calculated by comparing the metalens image and the image reconstructed by our framework with the ground truth image. A statistical hypothesis test was performed through a two-sided paired t-test on the performance difference between the metalens image and the image reconstructed by our framework [significance level P=10−4, (a) 1.055×10−39, (b) 3.886×10−35, (c) 1.363×10−48, (d) 2.311×10−35, and (e) 2.150×10−38].

Fig. 6. (a) and (b) White and black USAF images captured by the metalens imaging system, respectively. (c) and (d) White and black USAF images restored by our framework, respectively. The image in the red boxes shows the enlarged image in the central region indicated as red box. The scale bars in the original and enlarged images are 3 and 0.5 mm, respectively, indicating the distance on the image sensor.

Fig. 7. Object detection results using a pre-trained SSD model on (a), (d) the original images, (b), (e) the metalens images, and (c), (f) the images restored by our framework. The pre-trained SSD model could not detect any objects in the metalens images accurately; however, it successfully captured multiple classes and objects in images restored by our framework.