Deep-learning enhanced high-quality imaging in metalens-integrated camera.

• Yanxiang Zhang, Yue Wu, Chunyu Huang, Zi-Wen Zhou, Muyang Li, zaichen zhang, and Ji Chen
• received 02/09/2024; accepted 04/03/2024; posted 04/09/2024; Doc. ID 521393
• Abstract: Benefitting from the characteristics of ultra-light, ultra-thin and flexibility in design, metalenses exhibit significant potential in the development of highly integrated cameras. However, the performances of metalens-integrated camera are constrained by their fixed architectures. Here we proposed a high-quality imaging method based on deep learning to overcome this constraint. We employed a multi-scale convolutional neural network (MSCNN) to train an extensive paired of high-quality and low-quality images obtained from convolutional imaging model. Through our method, the imaging resolution, contrast, and distortion have all been improved, resulting in a noticeable overall image quality with SSIM over 0.9 and an improvement in PSNR over 3dB. Our approach enables cameras to combine the advantages of high integration with enhanced imaging performances, revealing tremendous potential for future groundbreaking imaging technology.