Year: 2026
Type: article
Abstract: Metalenses offer wafer-scale, ultra-thin optics for compact cameras, but strong chromatic and field-dependent aberrations still limit their practical use. Deep learning-based aberration correction can restore high-quality images from metalens captures, but current pipelines typically require hundreds to thousands of paired images per device. We address this data bottleneck by formulating metalens aberration synthesis as a deterministic, metalens-conditioned image-to-image translation problem. A generator is trained on a dataset of paired metalens and conventional images from a mass-producible metalens, then used to transform photographs into metalens-style outputs that reproduce realistic chromatic aberration, field-dependent blur, and spatial distortion. On a test set, the proposed translator reduces LPIPS(VGG) from 0.305 to 0.117 (∼62%) compared with a state-of-the-art transformer-based restoration baseline. Once trained, the translator can generate 600 synthetic metalens-style images in roughly 30 s on a single GPU, versus about 30 min for real metalens acquisition, a [Formula: see text] reduction in data-collection time. These synthetic pairs alone suffice to train a metalens image restoration model, suggesting that our approach can help alleviate the data bottleneck in future metalens imaging research.
Source: Scientific Reports
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,690
Funders: National Research Foundation, Hanyang University, Ministry of Culture, Sports and Tourism, National Research Foundation of Korea, Korea Creative Content Agency, Iran Telecommunication Research Center, Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion
OpenAlex ID: W7124927936