# How to Train Neural Networks for Flare Removal

arXiv: https://arxiv.org/abs/2011.12485 · HTML: https://mlsanity.com/paper/2011.12485/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2020.

## Built on by (most cited first, 30 of 50)

- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [Flare7K: A Phenomenological Nighttime Flare Removal Dataset](https://mlsanity.com/paper/2210.06570/) (2022)
- [Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond](https://mlsanity.com/paper/2306.04236/) (2023)
- [Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior](https://mlsanity.com/paper/2303.15046/) (2023)
- [Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery](https://mlsanity.com/paper/2308.16460/) (2023)
- [Blind Image Decomposition](https://mlsanity.com/paper/2108.11364/) (2021)
- [MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal](https://mlsanity.com/paper/2406.18079/) (2024)
- [MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results](https://mlsanity.com/paper/2209.07052/) (2022)
- [GLARE: A Dataset for Traffic Sign Detection in Sun Glare](https://mlsanity.com/paper/2209.08716/) (2022)
- [LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal](https://mlsanity.com/paper/2510.15868/) (2025)
- [Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration](https://mlsanity.com/paper/2408.09241/) (2024)
- [MIPI 2023 Challenge on Nighttime Flare Removal: Methods and Results](https://mlsanity.com/paper/2305.13770/) (2023)
- [The BRAVO Semantic Segmentation Challenge Results in UNCV2024](https://mlsanity.com/paper/2409.15107/) (2024)
- [UniSER: A Foundation Model for Unified Soft Effects Removal](https://mlsanity.com/paper/2511.14183/) (2025)
- [FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering](https://mlsanity.com/paper/2510.09995/) (2025)
- [Model Monitoring and Robustness of In-Use Machine Learning Models: Quantifying Data Distribution Shifts Using Population Stability Index](https://mlsanity.com/paper/2302.00775/) (2023)
- [Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal](https://mlsanity.com/paper/2404.00313/) (2024)
- [First Place Solution to the ECCV 2024 BRAVO Challenge: Evaluating Robustness of Vision Foundation Models for Semantic Segmentation](https://mlsanity.com/paper/2409.17208/) (2024)
- [Removing Image Artifacts From Scratched Lens Protectors](https://mlsanity.com/paper/2302.05746/) (2023)
- [Using simulation to quantify the performance of automotive perception systems](https://mlsanity.com/paper/2303.00983/) (2023)
- [Toward Real Flare Removal: A Comprehensive Pipeline and A New Benchmark](https://mlsanity.com/paper/2306.15884/) (2023)
- [Strong and Controllable Blind Image Decomposition](https://mlsanity.com/paper/2403.10520/) (2024)
- [MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results](https://mlsanity.com/paper/2404.19534/) (2024)
- [Flexible ViG: Learning the Self-Saliency for Flexible Object Recognition](https://mlsanity.com/paper/2406.18585/) (2024)
- [GN-FR:Generalizable Neural Radiance Fields for Flare Removal](https://mlsanity.com/paper/2412.08200/) (2024)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark](https://mlsanity.com/paper/2503.17027/) (2025)
- [DFDNet: Dynamic Frequency-Guided De-Flare Network](https://mlsanity.com/paper/2507.17489/) (2025)
- [DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal](https://mlsanity.com/paper/2508.02113/) (2025)
- [TransLight: Image-Guided Customized Lighting Control with Generative Decoupling](https://mlsanity.com/paper/2508.14814/) (2025)
- [Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal](https://mlsanity.com/paper/2511.17353/) (2025)

## Abstract (arXiv)

When a camera is pointed at a strong light source, the resulting photograph may contain lens flare artifacts. Flares appear in a wide variety of patterns (halos, streaks, color bleeding, haze, etc.) and this diversity in appearance makes flare removal challenging. Existing analytical solutions make strong assumptions about the artifact's geometry or brightness, and therefore only work well on a small subset of flares. Machine learning techniques have shown success in removing other types of artifacts, like reflections, but have not been widely applied to flare removal due to the lack of training data. To solve this problem, we explicitly model the optical causes of flare either empirically or using wave optics, and generate semi-synthetic pairs of flare-corrupted and clean images. This enables us to train neural networks to remove lens flare for the first time. Experiments show our data synthesis approach is critical for accurate flare removal, and that models trained with our technique generalize well to real lens flares across different scenes, lighting conditions, and cameras.