| dc.description.abstract | In today’s world, optical lenses play a vital role in our daily lives and are widely used in various technological devices, including smartphones, self-driving sensors, and augmented reality (AR) / virtual reality (VR) equipment. These devices are trending towards thinner and lighter consumer electronics, creating a demand for the continuous miniaturization of optical components. However, traditional refractive lenses, such as convex or concave materials, are bulky and severely hinder the miniaturization of optical components.
In recent years, there has been significant progress in the development of nanostructures on sub-wavelength scales, leading to a growing interest in metasurfaces. These nanostructured metasurfaces utilize collective resonances to control the characteristics of electromagnetic waves at the nano-scale, opening up possibilities for the creation of miniature optical components.
We conducted an analysis of the optical properties of the metasurface lens and used two sequential AI models to address the blurriness and color cast issues in images captured by the metasurface lens due to material loss and structural scattering of the metasurface lens. In terms of AI models, we used an Autoencoder and CodeFormer to correct color cast and reconstruct image details, respectively. We successfully addressed color cast in all facial images using the Autoencoder model, while the CodeFormer model effectively reconstructed standard frontal faces, facial expressions, and side profile images. Through these two sequential AI models, we have increased the potential for the application of metasurface lenses in daily life. | en_US |