EventGait：面向事件流的鲁棒步态识别
EventGait: Towards Robust Gait Recognition with Event Streams
把事件相机引入步态识别，用脉冲专家混合（MoSE）建模微秒级动态、用跨模态结构对齐（CroSA）借助大视觉基础模型蒸馏稠密形状表征，为低光照/高动态场景下的人体运动识别提供了可复用的双流事件表征方案。
原文依据 we propose EventGait, an end-to-end dual-stream framework that separately models motion and shape while preserving the advantages of events
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论步态识别能够实现非侵入式、保护隐私的身份识别，但传统相机在非受控环境中受光照与运动敏感性影响而性能下降。本文探索使用事件相机进行步态识别，事件相机具备微秒级时间分辨率与高动态范围，能够自然捕获鲁棒的动态线索并抑制静态噪声。现有基于事件的方法通常将事件流在长时间窗口内聚合成事件图像，从而丢弃了对步态识别至关重要的细粒度运动动态。为此，我们提出 EventGait，一个端到端双流框架，在保留事件优势的同时分别建模运动与形状。我们的动态流采用具有多样神经元常数的脉冲专家混合（MoSE），以在复杂运动与光照场景中实现鲁棒的动态感知；静态流则通过跨模态结构对齐（CroSA）借助大视觉基础模型学习稠密形状表征。为弥补大规模事件步态数据集的缺失，我们引入一套合成流程并发布两个新基准：SUSTech1K-E 与 CCGR-Mini-E。大量实验表明，基于事件的步态识别不仅在常规条件下取得与基于相机的步态识别相当的结果，而且在低光照场景下显著优于后者。我们的方法在合成与真实事件步态基准上均取得新的最优性能，凸显了事件驱动步态分析的鲁棒性与潜力。代码与数据集已发布于 https://github.com/QUEAHREN/EventGait。
英文原文摘要 1673 字符
Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensitivity in conventional cameras. In this work, we explore gait recognition using event cameras, which offer microsecond temporal resolution and high dynamic range, naturally capturing robust dynamic cues and suppressing static noise. Existing event-based approaches typically aggregate event streams into event images over long time windows, thereby discarding fine-grained motion dynamics critical for gait recognition. Therefore, we propose EventGait, an end-to-end dual-stream framework that separately models motion and shape while preserving the advantages of events. Our dynamic stream leverages a Mixture of Spiking Experts (MoSE) with diverse neuron constants for robust dynamic perception across complex motion and illumination scenes, while the static stream learns dense shape representations via Cross-modal Structural Alignment (CroSA) with large vision foundation models. To address the absence of large-scale event-based gait datasets, we introduce a synthesis pipeline and release two new benchmarks: SUSTech1K-E and CCGR-Mini-E. Extensive experiments have shown that event-based gait recognition not only achieves results comparable to camera-based gait recognition under normal conditions but also significantly outperforms it in low-light scenarios. Our approach sets a new state of the art on both synthesized and real-world event-based gait benchmarks, highlighting the robustness and potential of event-driven gait analysis. The code and datasets are released at https://github.com/QUEAHREN/EventGait.