Diffusion Algorithm for Metalens Optical Aberration Correction

TL;DR

This paper introduces a diffusion-based algorithm leveraging a pre-trained model to correct chromatic aberrations in metalens images, enabling high-quality, full-color image reconstruction from distorted inputs.

Contribution

It proposes a novel dual-branch diffusion model that fuses structure and color cues for aberration correction in metalens imaging, outperforming existing methods.

Findings

Significantly improves image sharpness and color accuracy.

Outperforms existing deblurring and pansharpening techniques.

Effectively restores high-frequency details in distorted images.

Abstract

Metalenses offer a path toward creating ultra-thin optical systems, but they inherently suffer from severe, spatially varying optical aberrations, especially chromatic aberration, which makes image reconstruction a significant challenge. This paper presents a novel algorithmic solution to this problem, designed to reconstruct a sharp, full-color image from two inputs: a sharp, bandpass-filtered grayscale ``structure image'' and a heavily distorted ``color cue'' image, both captured by the metalens system. Our method utilizes a dual-branch diffusion model, built upon a pre-trained Stable Diffusion XL framework, to fuse information from the two inputs. We demonstrate through quantitative and qualitative comparisons that our approach significantly outperforms existing deblurring and pansharpening methods, effectively restoring high-frequency details while accurately colorizing the image.