# Learning to See Through Flare

arXiv: https://arxiv.org/abs/2508.13907 · HTML: https://mlsanity.com/paper/2508.13907/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 98 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Builds on (most cited first, 30 of 38)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [Pay Attention to MLPs](https://mlsanity.com/paper/2105.08050/) (2021)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Fast Sampling of Diffusion Models via Operator Learning](https://mlsanity.com/paper/2211.13449/) (2022)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Spectral Representations for Convolutional Neural Networks](https://mlsanity.com/paper/1506.03767/) (2015)
- [Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink](https://mlsanity.com/paper/2103.06504/) (2021)
- [MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction](https://mlsanity.com/paper/2204.07908/) (2022)
- [COCO-GAN: Generation by Parts via Conditional Coordinating](https://mlsanity.com/paper/1904.00284/) (2019)
- [Deep Optics for Single-shot High-dynamic-range Imaging](https://mlsanity.com/paper/1908.00620/) (2019)
- [InfinityGAN: Towards Infinite-Pixel Image Synthesis](https://mlsanity.com/paper/2104.03963/) (2021)
- [How to Train Neural Networks for Flare Removal](https://mlsanity.com/paper/2011.12485/) (2020)
- [Flare7K: A Phenomenological Nighttime Flare Removal Dataset](https://mlsanity.com/paper/2210.06570/) (2022)

## Abstract (arXiv)

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 106 times the sensor saturation threshold I_textrmsat, 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.