用无标签数据训练夜间镜头眩光去除模型，提升稳定性与效果
Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
- 构建自适应伪标签库，通过无参考质量评估和动量更新优化标签
- 设计眩光感知对比损失，使模型在局部特征上区分眩光与真实内容
- 无需成对标注，适用于多种眩光场景，适合实际应用部署
镜头眩光去除因眩光区域范围大且与场景结构纠缠而困难，现有方法严重依赖大规模成对数据。本文提出一种半监督眩光去除框架，通过联合优化伪标签可靠性与表征判别性，实现从无标签图像中稳定学习。提出自适应伪标签仓库，通过无参考质量评估、动量更新和无效标签过滤，有效缓解误差累积。同时设计眩光感知对比损失，将含眩光输入显式视为负样本，进行局部块级对比学习，促使模型学习到对眩光具有判别力但与可靠伪标签保持一致的表征。在多个眩光基准测试上的大量实验表明，该框架具备模型无关性，能持续提升性能与鲁棒性。
原文摘要 · Abstract (English)
Lens flare removal is challenging due to the large spatial extent of flare artifacts and their entanglement with scene structures, while existing methods heavily rely on large-scale paired data. We propose a semi-supervised flare removal framework that enables stable learning from unlabeled images by jointly addressing pseudo-label reliability and representation discrimination. We propose an adaptive pseudo-label repository that progressively refines pseudo supervision through no-reference quality assessment, momentum-based updates, and invalid label filtering, effectively mitigating error accumulation. Moreover, we propose a flare-aware contrastive loss that explicitly treats flare-contaminated inputs as negatives and performs patch-level contrastive learning, encouraging representations that are discriminative against flare patterns while remaining consistent with reliable pseudo targets. Extensive experiments on multiple flare benchmarks demonstrate that the proposed framework is model-agnostic and consistently improves performance and robustness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。