Computational Imaging for Simultaneous Image Restoration and Super-Resolution Image Reconstruction of Single-Lens Diffractive Optical System

Abstract

Diffractive optical elements (DOEs) are difficult to apply in natural scenes imaging covering the visible bandwidth-spectral due to their strong chromatic aberration and the decrease in diffraction efficiency. Advances in computational imaging make it possible. In this paper, the image quality degradation model of DOE in bandwidth-spectral imaging is established to quantitatively analyze its degradation process. We design a DDZMR network for a single-lens diffractive lens computational imaging system, which can simultaneously perform image restoration and image super-resolution reconstruction on degraded images. The multimodal loss function was created to evaluate the reconstruction of the diffraction imaging degradation by the DDZMR network. The prototype physical prototype of the single-lens harmonic diffraction computational imaging system (SHDCIS) was built to verify the imaging performance. SHDCIS testing showed that optical chromatic aberration is corrected by computational reconstruction, and the computational imaging module can interpret an image and restore it at 1.4 times the resolution. We also evaluated the performance of the DDZMR model using the B100 and Urban100 datasets. Mean Peak Signal to Noise Ratio (PSNR)/Structural Similarity (SSIM) were, respectively, 32.09/0.8975 and 31.82/0.9247, which indicates that DDZMR performed comparably to the state-of-the-art (SOTA) methods. This work can promote the development and application of diffractive imaging systems in the imaging of natural scenes in the bandwidth-spectrum.

Keywords

• harmonic diffractive optical element
• computational imaging
• image restoration
• image super-resolution