Learning to See Through Flare

2025-08-19

AI Summary

Laser glare can easily saturate machine vision systems or cause permanent sensor damage, severely degrading environmental perception. To address this, we propose NeuSee—a novel framework enabling high-fidelity imaging across the full visible spectrum while providing active laser protection. NeuSee jointly optimizes a neuralized diffractive optical element (DOE) and a frequency-domain Mamba-GAN network, trained end-to-end via adversarial learning and accelerated through heterogeneous parallel computation. It achieves robust glare removal under dynamic variations in laser wavelength, intensity, incident angle, and ambient illumination. Trained on 100,000 images, NeuSee suppresses laser irradiance up to one million times the sensor’s saturation threshold. In real-world open environments, it improves restored image PSNR by 10.1% over state-of-the-art methods—marking the first solution to simultaneously achieve full-spectrum fidelity and adaptive, hardware-aware laser defense.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Machine vision systems are susceptible to laser flare, where unwanted intense laser illumination blinds and distorts its perception of the environment through oversaturation or permanent damage to sensor pixels. We introduce NeuSee, the first computational imaging framework for high-fidelity sensor protection across the full visible spectrum. It jointly learns a neural representation of a diffractive optical element (DOE) and a frequency-space Mamba-GAN network for image restoration. NeuSee system is adversarially trained end-to-end on 100K unique images to suppress the peak laser irradiance as high as $10^6$ times the sensor saturation threshold $I_{ extrm{sat}}$, the point at which camera sensors may experience damage without the DOE. Our system leverages heterogeneous data and model parallelism for distributed computing, integrating hyperspectral information and multiple neural networks for realistic simulation and image restoration. NeuSee takes into account open-world scenes with dynamically varying laser wavelengths, intensities, and positions, as well as lens flare effects, unknown ambient lighting conditions, and sensor noises. It outperforms other learned DOEs, achieving full-spectrum imaging and laser suppression for the first time, with a 10.1% improvement in restored image quality.

Problem

• Suppresses intense laser flare blinding machine vision sensors
• Restores high-fidelity imaging across full visible spectrum
• Handles dynamic laser wavelengths, intensities and ambient conditions

Innovation

• Neural diffractive optical element for protection
• Frequency-space Mamba-GAN network for restoration
• Adversarial training with hyperspectral information integration