Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares

Xiyu Zhu, Wei Wang, Kui Jiang, Zhengguo LiICML 2026 · OpenReview

Abstract

Lens flare removal is challenging due to the large spatial extent of flare artifacts and their entangle-ment with scene structures, while existing meth-ods heavily rely on large-scale paired data. We propose a semi-supervised flare removal frame-work that enables stable learning from unlabeled images by jointly addressing pseudo-label relia-bility and representation discrimination. We pro-pose an adaptive pseudo-label repository that pro-gressively refines pseudo supervision through no-reference quality assessment, momentum-based updates, and invalid label filtering, effectively mit-igating error accumulation. Moreover, we pro-pose a flare-aware contrastive loss that explic-itly treats flare-contaminated inputs as negatives and performs patch-level contrastive learning, en-couraging representations that are discriminative against flare patterns while remaining consistent with reliable pseudo targets. Extensive experi-ments on multiple flare benchmarks demonstrate that the proposed framework is model-agnostic and consistently improves performance and ro-bustness.
BibTeX
@inproceedings{zhu2026semi,
  author = {Xiyu Zhu and Wei Wang and Kui Jiang and Zhengguo Li},
  title = {{Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares}},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
  url = {https://openreview.net/forum?id=WTg6EIcXso},
}

Loading related content...

Figure