A Gradient-Regularized Deep Learning Method for Restoring Image in Myopic Vision

Kebin Contreras; Luis Toscano-Palomino; Rafael Torres; Jorge Bacca

cs.CVOct 13, 2026

A Gradient-Regularized Deep Learning Method for Restoring Image in Myopic Vision

Authors: Kebin Contreras, Luis Toscano-Palomino, Rafael Torres, Jorge Bacca

Organizations: Physics School Univ. Industrial of Santander Bucaramanga, Colombia · Dept. of Computer Science Univ. Industrial of Santander Bucaramanga, Colombia

Abstract

Myopic vision degrades the quality of human vision due to spherical eye defocus aberrations that impair the perception of fine spatial details. To address this limitation, this work proposes a deep learning-based approach to computationally design transformed images that allow individuals with myopia in fixed distance to perceive scenes with enhanced clarity. The method trains a neural network to counteract defocus aberrations modeled using the second-order Zernike polynomial $Z_2^0$ . The approach employs a U-Net architecture trained with a loss function combining reconstruction error minimization with spatial difference structural preservation through $\ell_1$ regularization. Training is carried out exclusively on the KITTI dataset, while testing is performed on DIV2K and ImageNet datasets, demonstrating generalization across diverse image distributions. Under myopic conditions modeled by $Z_2^0$ , baseline performance shows visual degradation with PSNR values ranging from 19.47 to 27.42 dB across datasets and severity levels. The proposed gradient-regularized method achieves consistent improvements, delivering PSNR gains ranging from 1.48 to 7.34 dB and significantly lower perceptual compared to classical baselines.

Figures & tables

Fig. 1: Proposed computational pre-compensation pipeline. The process involves modeling the myopic visual system using Zernike polynomials ( $Z_{2}^{0}$ ), applying a deep learning-based compensation model ( $f_{\theta}$ ), and evaluating the restored result ( $h*f_{\theta}$ ) through signal and perceptual metrics.

S = 0.50 (Mild Aberration)
Method / Severity (S)	KITTI [ 12 ]			DIV2K [ 14 ]			ImageNet [ 15 ]
Method / Severity (S)	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$	SSIM $\uparrow$	PSNR $\uparrow$	LPIPS $\downarrow$
Baseline (Uncorrected)	0.848 $\pm$ 0.047	26.10 $\pm$ 1.43	0.237 $\pm$ 0.027	0.674 $\pm$ 0.115	23.31 $\pm$ 2.64	0.386 $\pm$ 0.084	0.840 $\pm$ 0.076	27.42 $\pm$ 3.29	0.237 $\pm$ 0.069
Wiener Deconvolution	0.895 $\pm$ 0.032	26.96 $\pm$ 1.47	0.080 $\pm$ 0.018	0.746 $\pm$ 0.092	23.77 $\pm$ 2.80	0.304 $\pm$ 0.093	0.882 $\pm$ 0.057	28.26 $\pm$ 3.42	0.105 $\pm$ 0.047
UNet (MSE Loss)	0.989 $\pm$ 0.003	34.73 $\pm$ 0.78	0.034 $\pm$ 0.009	0.897 $\pm$ 0.056	28.29 $\pm$ 3.21	0.220 $\pm$ 0.083	0.973 $\pm$ 0.024	34.61 $\pm$ 3.12	0.056 $\pm$ 0.035
Ours (Unet + Reg)	0.993 $\pm$ 0.003	33.44 $\pm$ 1.00	0.023 $\pm$ 0.009	0.900 $\pm$ 0.065	27.79 $\pm$ 3.38	0.183 $\pm$ 0.078	0.968 $\pm$ 0.037	34.60 $\pm$ 4.36	0.041 $\pm$ 0.031

TABLE I: Comparative quantitative evaluation of image restoration across datasets under varying myopic defocus severities (

S

). Values represent Mean

\pm

Standard Deviation. The best results are highlighted in bold, while the second-best are underlined , arrows (

\uparrow

and

\downarrow

Fig. 2: Hyperparameter tuning for the gradient regularization weight $\alpha$ . The PSNR is plotted for different values of $\alpha$ , showing that $\alpha=0.01$ achieves the best performance.

Fig. 3: Cross-domain visual results comparing myopic with severity level 2.0 degradation and gradient-regularized correction. PSNR values are shown for KITTI (training), DIV2K (natural), and ImageNet (object-centric) datasets.

Image Restoration

Image restoration uses computational methods to recover useful visual content from noisy, blurred, low-resolution, or otherwise degraded images.

See all 372 papers

Physics-consistent deep learning for blind aberration recovery in mobile optics
Mar 5, 2026Kartik Jhawar, Tamo Sancho Miguel Tandoc, Khoo Jun Xuan +1Physics-Guided Image Restoration Computational Imaging
Institute for Digital Molecular Analytics and Science (IDMxS), Nanyang Technological University, Singapore 636921 · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798
Depth from Defocus via Direct Optimization
Feb 18, 2026Holly Jackson, Caleb Adams, Ignacio Lopez-Francos +1Depth Estimation Computational Imaging
⋆University of California, Berkeley, California, USA · † NASA Ames Research Center, Moffett Field, California, USA · ‡ KBR, Houston, Texas, USA
ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring
Jun 4, 2026Tu Vo, Chan Y. ParkImage Deblurring Computational Imaging
KC Machine Learning Lab Seoul, South Korea 06181

Mar 5, 2026J/K move · Enter open · S save

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

Kartik Jhawar, Tamo Sancho Miguel Tandoc, Khoo Jun Xuan, Wang Lipo

Institute for Digital Molecular Analytics and Science (IDMxS), Nanyang Technological University, Singapore 636921 · School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798

Physics-Guided Image Restoration Computational Imaging Image Inverse Problems Image Deblurring

Open paper AskPDF arXiv

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.

Abstract

Image Restoration

Explore similar work

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

Depth from Defocus via Direct Optimization

ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring