Learning to See Through Dazzle

TL;DR

This paper introduces a wavefront-coded phase mask combined with a sandwich GAN architecture to effectively restore images degraded by laser dazzle, enabling machine vision systems to operate safely under intense laser exposure.

Contribution

The paper presents a novel SGAN architecture with Fourier features and physics-based training to suppress laser-induced image saturation and damage, advancing laser-resistant machine vision.

Findings

Outperforms state-of-the-art image restoration methods across various conditions.

Successfully suppresses laser irradiance up to 10^6 times sensor saturation.

Effective on both synthetic and laboratory-collected data.

Abstract

Machine vision is susceptible to laser dazzle, where intense laser light can blind and distort its perception of the environment through oversaturation or permanent damage to sensor pixels. Here we employ a wavefront-coded phase mask to diffuse the energy of laser light and introduce a sandwich generative adversarial network (SGAN) to restore images from complex image degradations, such as varying laser-induced image saturation, mask-induced image blurring, unknown lighting conditions, and various noise corruptions. The SGAN architecture combines discriminative and generative methods by wrapping two GANs around a learnable image deconvolution module. In addition, we make use of Fourier feature representations to reduce the spectral bias of neural networks and improve its learning of high-frequency image details. End-to-end training includes the realistic physics-based synthesis of a large set of training data from publicly available images. We trained the SGAN to suppress the peak laser irradiance as high as $10^6$ times the sensor saturation threshold - the point at which camera sensors may experience damage without the mask. The trained model was evaluated on both a synthetic data set and data collected from the laboratory. The proposed image restoration model quantitatively and qualitatively outperforms state-of-the-art methods for a wide range of scene contents, laser powers, incident laser angles, ambient illumination strengths, and noise characteristics.