Physics-consistent deep learning for blind aberration recovery in mobile optics

TL;DR

This paper introduces Lens2Zernike, a physics-consistent deep learning framework that accurately recovers optical aberration parameters from a single blurred image, enabling stable deconvolution and improved mobile photography quality.

Contribution

It presents the first integrated deep learning approach that combines supervision across optical domains with physics-based constraints for aberration recovery.

Findings

35% improvement over coefficient-only baselines

Outperforms existing deep learning methods in regression accuracy

Enables stable non-blind deconvolution for mobile images

Abstract

Mobile photography is often limited by complex, lens-specific optical aberrations. While recent deep learning methods approach this as an end-to-end deblurring task, these "black-box" models lack explicit optical modeling and can hallucinate details. Conversely, classical blind deconvolution remains highly unstable. To bridge this gap, we present Lens2Zernike, a deep learning framework that blindly recovers physical optical parameters from a single blurred image. To the best of our knowledge, no prior work has simultaneously integrated supervision across three distinct optical domains. We introduce a novel physics-consistent strategy that explicitly minimizes errors via direct Zernike coefficient regression (z), differentiable physics constraints encompassing both wavefront and point spread function derivations (p), and auxiliary multi-task spatial map predictions (m). Through an ablation study on a ResNet-18 backbone, we demonstrate that our full multi-task framework (z+p+m) yields a 35% improvement over coefficient-only baselines. Crucially, comparative analysis reveals that our approach outperforms two established deep learning methods from previous literature, achieving significantly lower regression errors. Ultimately, we demonstrate that these recovered physical parameters enable stable non-blind deconvolution, providing substantial in-domain improvement on the patented Institute for Digital Molecular Analytics and Science (IDMxS) Mobile Camera Lens Database for restoring diffraction-limited details from severely aberrated mobile captures.