Deep Event Visual Odometry（深度事件视觉里程计）
Deep Event Visual Odometry
AI总结：
针对现有单目事件视觉里程计性能不足、依赖额外传感器的问题，提出纯单目事件系统DEVO，通过新型深度块选择机制稀疏追踪事件块，在七个基准上误差最高降97%，性能接近或超越双目/惯性方法。
摘要：
事件相机为高速运动及恶劣光照条件下的相机位姿追踪提供了极具潜力的解决方案。尽管前景可观，现有的基于事件的单目视觉里程计（VO）方法在最新基准测试中表现仍有局限。为解决这一问题，部分方法借助IMU、双目事件相机或帧式相机等额外传感器。但这类额外传感器会提升成本、增加系统复杂度，限制了事件相机在实际设备中的应用；且依赖帧式相机会让系统易受运动模糊和HDR问题影响。为摆脱对额外传感器的依赖，突破单事件相机的性能瓶颈，我们提出Deep Event VO（DEVO，深度事件视觉里程计）——首个在大量真实世界基准测试中表现优异的纯单目事件系统。DEVO会随时间稀疏追踪选定的事件块，其核心组件是一种专为事件数据设计的新型深度块选择机制。在七个真实世界基准测试中，与纯事件方法相比，我们的方法将位姿追踪误差最高降低了97%，性能通常超越或接近双目或惯性融合方法。代码可在https://github.com/tum-vision/DEVO获取。
英文摘要：
Event cameras offer the exciting possibility of tracking the camera's pose during high-speed motion and in adverse lighting conditions. Despite this promise, existing event-based monocular visual odometry (VO) approaches demonstrate limited performance on recent benchmarks. To address this limitation, some methods resort to additional sensors such as IMUs, stereo event cameras, or frame-based cameras. Nonetheless, these additional sensors limit the application of event cameras in real-world devices since they increase cost and complicate system requirements. Moreover, relying on a frame-based camera makes the system susceptible to motion blur and HDR. To remove the dependency on additional sensors and to push the limits of using only a single event camera, we present Deep Event VO (DEVO), the first monocular event-only system with strong performance on a large number of real-world benchmarks. DEVO sparsely tracks selected event patches over time. A key component of DEVO is a novel deep patch selection mechanism tailored to event data. We significantly decrease the pose tracking error on seven real-world benchmarks by up to 97% compared to event-only methods and often surpass or are close to stereo or inertial methods. Code is available at https://github.com/tum-vision/DEVO
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
