Achromatic Imaging Systems with Flat Lenses Enabled by Deep Learning

Motivated by their great potential to reduce the size, cost, and weight, flat lenses, a category that includes diffractive lenses and metalenses, are rapidly emerging as key components with the potential to replace the traditional refractive optical elements in modern optical systems. Yet, the inherently strong chromatic aberration of these flat lenses is significantly impairing their performance in systems based on polychromatic illumination or passive ambient light illumination, stalling their widespread implementation. Hereby, we provide a promising solution and demonstrate high-quality imaging based on flat lenses over the entire visible spectrum. Our approach is based on creating a novel data set of color outdoor images taken with our flat lens and using this data set to train a deep-learning model for chromatic aberrations correction. Based on this approach, we show unprecedented imaging results not only in terms of qualitative measures but also in quantitative terms of the peak signal-to-noise ratio (PSNR) and structure similarity index (SSIM) scores of the reconstructed images. The results pave the way for the implementation of flat lenses in advanced polychromatic imaging systems.