SAFAformer: Scale-Aware Frequency-Adaptive Guidance for Nighttime Flare Removal

Wei Dong, Guodong Fan, Fan Zhang, Min Gan, Guangyong Chen, C. L. Philip Chen

Abstract

Nighttime flare removal is challenging due to the difficulty of acquiring real-world paired data. Existing methods, trained on synthetic pipelines, often struggle to generalize to real-world scenarios. A key limitation of these pipelines is their focus on single-flare scenes, whereas real-world conditions frequently involve more complex cases, such as multi-flare and composite flare scenarios, which are difficult to simulate effectively. This discrepancy significantly hampers model performance in practical applications. Through detailed analysis, we uncover a fundamental characteristic of flare degradation: regardless of whether the scene is synthetic single-flare, real-world single-flare, or multi-flare, the degradation information exhibits a similar distribution across frequency subbands—predominantly concentrated in the low-frequency region, with a minor presence in the high-frequency region. Notably, the severity of the glare effect correlates with an even stronger concentration in the low-frequency domain. This finding suggests that targeted frequency modeling can bridge the gap between synthetic and real-world domains, forming a principled approach to improving generalization. Building on this insight, we propose the Scale-Aware Frequency-Adaptive Guidance Network for Nighttime Flare Removal (SAFAformer), which integrates a Frequency-Adaptive Guidance Module (FAGM) and a Scale-Aware Transformer Block (SATB) to leverage frequency-domain properties during training. Extensive experiments demonstrate that SAFAformer achieves state-of-the-art performance in flare removal compared to existing methods. Our code and pre-trained models are available on GitHub for validation.
BibTeX
@article{dong2026safaformer,
  author = {Wei Dong and Guodong Fan and Fan Zhang and Min Gan and Guangyong Chen and C. L. Philip Chen},
  title = {{SAFAformer: Scale-Aware Frequency-Adaptive Guidance for Nighttime Flare Removal}},
  journal = {IEEE Trans. Circuits Syst. Video Technol.},
  year = {2026},
  doi = {10.1109/tcsvt.2025.3595933},
}

Loading related content...

Figure