Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal

2025-11-21

AI Summary

In compact optical systems, stray-light-induced depth-agnostic, spatially non-uniform veiling glare severely degrades image quality, interferes with aberration correction, and defies accurate modeling by conventional scattering models—leading to a scarcity of high-fidelity paired training data and hindering data-driven approaches. To address this, we propose VeilGen, the first unsupervised single-image veiling glare latent generative model, which jointly leverages Stable Diffusion priors and invertibility constraints to achieve physically consistent decoupling of transmission maps and veiling glare. Building upon VeilGen, we design DeVeiler—a blind end-to-end veiling glare removal network operable without ground-truth pairs. Experiments demonstrate that VeilGen synthesizes highly realistic degraded images, while DeVeiler achieves state-of-the-art performance across diverse compact optical systems, striking an optimal balance between fine-detail preservation and veiling glare suppression.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Beyond the commonly recognized optical aberrations, the imaging performance of compact optical systems-including single-lens and metalens designs-is often further degraded by veiling glare caused by stray-light scattering from non-ideal optical surfaces and coatings, particularly in complex real-world environments. This compound degradation undermines traditional lens aberration correction yet remains underexplored. A major challenge is that conventional scattering models (e.g., for dehazing) fail to fit veiling glare due to its spatial-varying and depth-independent nature. Consequently, paired high-quality data are difficult to prepare via simulation, hindering application of data-driven veiling glare removal models. To this end, we propose VeilGen, a generative model that learns to simulate veiling glare by estimating its underlying optical transmission and glare maps in an unsupervised manner from target images, regularized by Stable Diffusion (SD)-based priors. VeilGen enables paired dataset generation with realistic compound degradation of optical aberrations and veiling glare, while also providing the estimated latent optical transmission and glare maps to guide the veiling glare removal process. We further introduce DeVeiler, a restoration network trained with a reversibility constraint, which utilizes the predicted latent maps to guide an inverse process of the learned scattering model. Extensive experiments on challenging compact optical systems demonstrate that our approach delivers superior restoration quality and physical fidelity compared with existing methods. These suggest that VeilGen reliably synthesizes realistic veiling glare, and its learned latent maps effectively guide the restoration process in DeVeiler. All code and datasets will be publicly released at https://github.com/XiaolongQian/DeVeiler.

Problem

• Removing veiling glare in compact optical systems caused by stray light
• Addressing spatially-varying glare that traditional scattering models cannot fit
• Generating realistic paired training data for veiling glare removal models

Innovation

• Generative model simulates veiling glare unsupervised
• Estimates latent optical transmission and glare maps
• Restoration network uses latent maps for inverse process