# Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery

arXiv: https://arxiv.org/abs/2308.16460 · HTML: https://mlsanity.com/paper/2308.16460/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [A Model-driven Deep Neural Network for Single Image Rain Removal](https://mlsanity.com/paper/2005.01333/) (2020)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [Polarized Reflection Removal with Perfect Alignment in the Wild](https://mlsanity.com/paper/2003.12789/) (2020)
- [A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing](https://mlsanity.com/paper/1708.03474/) (2017)
- [Single Image Reflection Removal through Cascaded Refinement](https://mlsanity.com/paper/1911.06634/) (2019)
- [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)
- [DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal](https://mlsanity.com/paper/2008.00767/) (2020)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Robust Reflection Removal with Reflection-free Flash-only Cues](https://mlsanity.com/paper/2103.04273/) (2021)
- [Semantically Contrastive Learning for Low-light Image Enhancement](https://mlsanity.com/paper/2112.06451/) (2021)
- [Automatic Flare Spot Artifact Detection and Removal in Photographs](https://mlsanity.com/paper/2103.04384/) (2021)
- [A review for Tone-mapping Operators on Wide Dynamic Range Image](https://mlsanity.com/paper/2101.03003/) (2021)

## Built on by (most cited first, 21 of 21)

- [LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal](https://mlsanity.com/paper/2510.15868/) (2025)
- [PIE: Physics-inspired Low-light Enhancement](https://mlsanity.com/paper/2404.04586/) (2024)
- [UniSER: A Foundation Model for Unified Soft Effects Removal](https://mlsanity.com/paper/2511.14183/) (2025)
- [Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal](https://mlsanity.com/paper/2502.10714/) (2025)
- [FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering](https://mlsanity.com/paper/2510.09995/) (2025)
- [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)
- [Instruct2See: Learning to Remove Any Obstructions Across Distributions](https://mlsanity.com/paper/2505.17649/) (2025)
- [MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results](https://mlsanity.com/paper/2404.19534/) (2024)
- [GN-FR:Generalizable Neural Radiance Fields for Flare Removal](https://mlsanity.com/paper/2412.08200/) (2024)
- [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)
- [Learning to Remove Lens Flare in Event Camera](https://mlsanity.com/paper/2512.09016/) (2025)
- [SLCFormer: Spectral-Local Context Transformer with Physics-Grounded Flare Synthesis for Nighttime Flare Removal](https://mlsanity.com/paper/2512.15221/) (2025)
- [ISETHDR: A Physics-based Synthetic Radiance Dataset for High Dynamic Range Driving Scenes](https://mlsanity.com/paper/2408.12048/) (2024)
- [Integrating Spatial and Frequency Information for Under-Display Camera Image Restoration](https://mlsanity.com/paper/2501.18517/) (2025)
- [Difflare: Removing Image Lens Flare with Latent Diffusion Model](https://mlsanity.com/paper/2407.14746/) (2024)
- [PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting](https://mlsanity.com/paper/2505.05183/) (2025)
- [Breaking Spatial Uniformity: Prior-Guided Mamba with Radial Serialization for Lens Flare Removal](https://mlsanity.com/paper/2605.07650/) (2026)
- [Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares](https://mlsanity.com/paper/2605.18156/) (2026)
- [LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography](https://mlsanity.com/paper/2606.06901/) (2026)
- [Lens Flare Removal and Reconstruction](https://mlsanity.com/paper/2609.39527/) (2026)

## Abstract (arXiv)

When taking images against strong light sources, the resulting images often contain heterogeneous flare artifacts. These artifacts can importantly affect image visual quality and downstream computer vision tasks. While collecting real data pairs of flare-corrupted/flare-free images for training flare removal models is challenging, current methods utilize the direct-add approach to synthesize data. However, these methods do not consider automatic exposure and tone mapping in image signal processing pipeline (ISP), leading to the limited generalization capability of deep models training using such data. Besides, existing methods struggle to handle multiple light sources due to the different sizes, shapes and illuminance of various light sources. In this paper, we propose a solution to improve the performance of lens flare removal by revisiting the ISP and remodeling the principle of automatic exposure in the synthesis pipeline and design a more reliable light sources recovery strategy. The new pipeline approaches realistic imaging by discriminating the local and global illumination through convex combination, avoiding global illumination shifting and local over-saturation. Our strategy for recovering multiple light sources convexly averages the input and output of the neural network based on illuminance levels, thereby avoiding the need for a hard threshold in identifying light sources. We also contribute a new flare removal testing dataset containing the flare-corrupted images captured by ten types of consumer electronics. The dataset facilitates the verification of the generalization capability of flare removal methods. Extensive experiments show that our solution can effectively improve the performance of lens flare removal and push the frontier toward more general situations.