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

• URL: http://arxiv.org/abs/2603.04999v1
• Date: Thu, 05 Mar 2026 09:44:07 GMT
• Title: Physics-consistent deep learning for blind aberration recovery in mobile optics
• Authors: Kartik Jhawar, Tamo Sancho Miguel Tandoc, Khoo Jun Xuan, Wang Lipo,
• Abstract summary: We present Lens2Zernike, a deep learning framework that blindly recovers physical optical parameters from a single blurred image.<n>We show that our full multi-task framework (z+p+m) yields a 35% improvement over coefficient-only baselines.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Learning to Remove Lens Flare in Event Camera [56.9171469873838]
  We present E-DeflareDeflare, the first framework for removing lens flare from event camera data.<n>We first establish the theoretical foundation by deriving a physics-grounded forward model of the non-linear suppression mechanism.<n> Empowered by this benchmark, we design E-DeflareNet, which achieves state-of-the-art restoration performance.
  arXiv  Detail & Related papers  (2025-12-09T18:59:57Z)
• Physics-Informed Graph Neural Network with Frequency-Aware Learning for Optical Aberration Correction [36.496034762040054]
  Optical aberrations significantly degrade image quality in microscopy, particularly when imaging deeper into samples.<n>We propose ZRNet, a physics-informed framework that jointly performs Zernike prediction and optical image Restoration.<n>Our approach achieves state-of-the-art performance in both image restoration and Zernike coefficient prediction across diverse microscopy modalities and biological samples with complex, large-amplitudes.
  arXiv  Detail & Related papers  (2025-12-05T12:58:55Z)
• OmniLens++: Blind Lens Aberration Correction via Large LensLib Pre-Training and Latent PSF Representation [72.72583225885636]
  This work proposes the OmniLens++ framework, which resolves two challenges that hinder the generalization ability of existing pipelines.<n>Experiments on diverse aberrations of real-world lenses and synthetic LensLib show that OmniLens++ exhibits state-of-the-art generalization capacity in blind aberration correction.
  arXiv  Detail & Related papers  (2025-11-21T10:41:54Z)
• From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy [12.900713570104749]
  We introduce three key contributions to learning-based 3D reconstruction in light field microscopy.<n>First, we construct the XLFM-Zebrafish benchmark, a large-scale dataset and evaluation suite for XLFM reconstruction.<n>Second, we propose Masked View Modeling for Light Fields (MVN-LF), a self-supervised task that learns angular priors by predicting occluded views.<n>Third, we formulate the Optical Rendering Consistency Loss (ORC Loss), a differentiable rendering constraint that enforces alignment between predicted volumes and their PSF-based forward projections.
  arXiv  Detail & Related papers  (2025-10-26T08:28:05Z)
• Wavefront Coding for Accommodation-Invariant Near-Eye Displays [1.7240671897505615]
  We present a new computational near-eye display method that addresses the vergence-accommodation conflict problem in stereoscopic displays.<n>Our system integrates a refractive lens eyepiece with a novel wavefront coding diffractive optical element.<n>We employ end-to-end learning to jointly optimize the wavefront-coding optics and the image pre-processing module.
  arXiv  Detail & Related papers  (2025-10-14T17:52:28Z)
• Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models [58.98742597810023]
  Vision models have to behave in a robust way to disturbances such as noise or blur.<n>This paper studies two datasets of blur corruptions, which we denote OpticsBench and LensCorruptions.<n> Evaluations for image classification and object detection on ImageNet and MSCOCO show that for a variety of different pre-trained models, the performance on OpticsBench and LensCorruptions varies significantly.
  arXiv  Detail & Related papers  (2025-04-25T17:23:47Z)
• Nonlocal Retinex-Based Variational Model and its Deep Unfolding Twin for Low-Light Image Enhancement [3.174882428337821]
  We propose a variational method for low-light image enhancement based on the Retinex decomposition.<n>A color correction pre-processing step is applied to the low-light image, which is then used as the observed input in the decomposition.<n>We extend the model by introducing its deep unfolding counterpart, in which the operators are replaced with learnable networks.
  arXiv  Detail & Related papers  (2025-04-10T14:48:26Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• Physics-Driven Turbulence Image Restoration with Stochastic Refinement [80.79900297089176]
  Image distortion by atmospheric turbulence is a critical problem in long-range optical imaging systems. Fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions. This paper proposes the Physics-integrated Restoration Network (PiRN) to help the network to disentangle theity from the degradation and the underlying image.
  arXiv  Detail & Related papers  (2023-07-20T05:49:21Z)
• Neural network analysis of neutron and X-ray reflectivity data: Incorporating prior knowledge for tackling the phase problem [141.5628276096321]
  We present an approach that utilizes prior knowledge to regularize the training process over larger parameter spaces. We demonstrate the effectiveness of our method in various scenarios, including multilayer structures with box model parameterization. In contrast to previous methods, our approach scales favorably when increasing the complexity of the inverse problem.
  arXiv  Detail & Related papers  (2023-06-28T11:15:53Z)
• Neural Invertible Variable-degree Optical Aberrations Correction [6.6855248718044225]
  We propose a novel aberration correction method with an invertible architecture by leveraging its information-lossless property. Within the architecture, we develop conditional invertible blocks to allow the processing of aberrations with variable degrees. Our method is evaluated on both a synthetic dataset from physics-based imaging simulation and a real captured dataset.
  arXiv  Detail & Related papers  (2023-04-12T01:56:42Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.