Lens flare occurs when shooting towards strong light sources, significantly degrading the visual quality of images. Due to the difficulty in capturing flare-corrupted and flare-free image pairs in the real world, existing datasets are typically synthesized in 2D by overlaying artificial flare templates onto background images. However, the lack of flare diversity in templates and the neglect of physical principles in the synthesis process hinder models trained on these datasets from generalizing well to real-world scenarios. To address these challenges, we propose a new physics-informed method for flare data generation, which consists of three stages: parameterized template creation, the laws of illumination-aware 2D synthesis, and physical engine-based 3D rendering, which finally gives us a miXed flare dataset that incorporates both 2D and 3D perspectives, namely FlareX. This dataset offers 9,500 2D templates derived from 95 flare patterns and 3,000 flare image pairs rendered from 60 3D scenes. Furthermore, we design a masking approach to obtain real-world flare-free images from their corrupted counterparts to measure the performance of the model on real-world images. Extensive experiments demonstrate the effectiveness of our method and dataset. The code and dataset are available at https://github.com/qulishen/FlareX.
@inproceedings{FlareX_lishenqu,
title={FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering},
author={Lishen, Qu and Zhihao, Liu and Jinshan, Pan and Shihao, Zhou and Jinglei, Shi and Duosheng, Chen and Jufeng, Yang},
booktitle={Advances in Neural Information Processing Systems},
year={2025}
}