首个系统性去除事件相机镜头眩光的方法，提升视觉系统可靠性。
Learning to Remove Lens Flare in Event Camera
- 基于物理规律建模镜头眩光的非线性抑制机制
- 构建了包含2.7万张模拟数据和真实配对数据的基准测试集
- 可显著改善下游任务性能，适合做事件相机图像处理的研究者
事件相机虽具备高时间分辨率和动态范围，但易受镜头眩光影响，导致严重退化。该光学伪影在事件流中形成复杂时空畸变，长期被忽视。本文提出E-Deflare，首个系统性去除事件相机镜头眩光的框架。通过推导基于物理的前向模型，揭示非线性抑制机制，进而构建E-Deflare基准：包含大规模模拟训练集E-Flare-2.7K和首个真实配对测试集E-Flare-R，由新设计的光学系统采集。基于此基准，设计E-DeflareNet，在重建性能上达到当前最优。大量实验验证方法有效性，并展示对下游任务的显著提升。代码与数据集已公开。
原文摘要 · Abstract (English)
Event cameras have the potential to revolutionize vision systems with their high temporal resolution and dynamic range, yet they remain susceptible to lens flare, a fundamental optical artifact that causes severe degradation. In event streams, this optical artifact forms a complex, spatio-temporal distortion that has been largely overlooked. We present E-Deflare, the first systematic framework for removing lens flare from event camera data. We first establish the theoretical foundation by deriving a physics-grounded forward model of the non-linear suppression mechanism. This insight enables the creation of the E-Deflare Benchmark, a comprehensive resource featuring a large-scale simulated training set, E-Flare-2.7K, and the first-ever paired real-world test set, E-Flare-R, captured by our novel optical system. Empowered by this benchmark, we design E-DeflareNet, which achieves state-of-the-art restoration performance. Extensive experiments validate our approach and demonstrate clear benefits for downstream tasks. Code and datasets are publicly available.
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。