事件结构谷：事件相机自动对焦的统一理论与实践框架
Event Structural Valley: A Unified Theoretical and Practical Framework for Event Camera Autofocus
提出事件率曲线在真实对焦处出现局部极小值的反直觉现象，并给出基于双峰约束的谷值检测方法，可启发基于事件相机的低层视觉任务（如去模糊、深度估计）利用事件率结构而非峰值进行状态估计。
原文依据 the true focus actually corresponds to a local minimum in the event-rate curve
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论动态环境下的自动对焦对传统帧基传感器仍具挑战性，在快速运动、低光照或高动态范围条件下往往失效。事件相机凭借微秒级时序分辨率和异步亮度检测，提供了一种有前景的替代方案。然而，典型的基于事件的自动对焦方法假设最清晰的焦点对应于最大事件率。本文揭示了一个反直觉但一致的现象：真实焦点实际上对应于事件率曲线中的局部极小值。我们从事件生成的物理原理出发理论推导了该行为，并表明随着离焦模糊增加，事件率先上升后下降，在焦距上形成双峰-谷结构。基于这一洞察，我们提出了基于事件结构谷的自动对焦（ESVA）框架，将两个主导峰之间的谷识别为真实焦点位置。ESVA 集成了结构平滑、一致性滤波和双峰约束，以在噪声和运动干扰下稳健地恢复谷值。在多个合成和真实世界数据集上的大量实验表明，ESVA 能够提供准确且稳定的焦点估计，在无需图像重建或监督的情况下持续优于现有的纯事件自动对焦方法。
英文原文摘要 1374 字符
Autofocus in dynamic environments remains challenging for conventional frame-based sensors, which often fail under fast motion, low light, or high dynamic range conditions. Event cameras, with microsecond temporal resolution and asynchronous brightness detection, offer a promising alternative. However, typical event-based autofocus methods assume that the sharpest focus corresponds to the maximum event rate. In this paper, we reveal a counterintuitive yet consistent phenomenon: the true focus actually corresponds to a local minimum in the event-rate curve. We theoretically derive this behavior from the physics of event generation and show that as defocus blur increases, the event rate first rises and then declines, forming a dual-peak-valley structure across focal distances. Based on this insight, we propose an Event Structural Valley-based Autofocus (ESVA) framework that identifies the valley between two dominant peaks as the true focal position. ESVA integrates structural smoothing, consistency filtering, and a dual-peak constraint to robustly recover the valley under noise and motion disturbances. Extensive experiments on multiple synthetic and real-world datasets demonstrate that ESVA delivers accurate and stable focus estimation, consistently outperforming existing event-only autofocus methods without requiring image reconstruction or supervision.