基于事件相机的无监督3D运动估计
Unsupervised 3d Motion Estimation Using Event Camera
利用事件相机的高时序分辨率和投影中的时空膨胀/收缩模式，为无监督3D运动估计（光流+深度运动）提供几何线索，可复用于事件相机下的运动估计与深度感知任务。
原文依据 Event cameras capture per-pixel brightness changes asynchronously with microsecond latency, providing high temporal resolution and motion continuity.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从二维观测中估计场景点的三维运动（通常由光流和深度方向运动参数化）是计算机视觉中的一个基本问题。现有的基于学习的方法通常依赖于从密集标注数据中进行监督回归，但其对标注的依赖以及对几何约束的有限利用限制了泛化能力，从而推动了无监督解决方案的研究。无监督三维运动估计具有挑战性，因为沿观察方向的运动不可观测，且光流与深度方向运动在几何上耦合，导致二者的分离存在歧义。事件相机以微秒级延迟异步捕获逐像素亮度变化，提供高时序分辨率和运动连续性。沿不同轴投影事件流可揭示编码深度变化和几何结构的时空膨胀与收缩模式，为无监督估计提供丰富线索。利用这些特性，我们提出了一种基于事件的无监督三维运动估计框架，联合建模光流和深度方向运动。我们首先推导出一种解析关系，从估计的光流中推断初始深度方向运动，并进一步使用方向性膨胀调制模块进行细化，该模块捕获事件投影中的水平和垂直膨胀-收缩模式。最后，在对比度最大化目标下，将深度方向运动纳入光流扭曲。在CarlaEvent3D数据集上的实验表明，我们的方法达到了有竞争力的精度和强大的泛化能力，推动了事件域中的无监督三维运动估计。
英文原文摘要 1667 字符
Estimating the 3D motion of scene points from 2D observations, typically parameterized by optical flow and motion in depth, is a fundamental problem in computer vision. Existing learning-based methods usually rely on supervised regression from densely labeled data, but their dependence on annotations and limited use of geometric constraints restricts generalization, motivating unsupervised solutions. Unsupervised 3D motion estimation is challenging because motion along the viewing direction is unobservable, and optical flow and motion in depth are geometrically coupled, making their separation ambiguous. Event cameras capture per-pixel brightness changes asynchronously with microsecond latency, providing high temporal resolution and motion continuity. Projecting event streams along different axes reveals spatiotemporal expansion and contraction patterns that encode depth variation and geometric structure, offering rich cues for unsupervised estimation. Leveraging these properties, we propose an unsupervised event-based 3D motion estimation framework that jointly models optical flow and motion in depth. We first derive an analytical relationship to infer initial motion in depth from estimated flow and further refine it using a directional expansion modulation module that captures horizontal and vertical expansion-contraction patterns in event projections. Finally, motion in depth is incorporated into optical flow warping under a contrast maximization objective. Experiments on the CarlaEvent3D dataset show that our method achieves competitive accuracy and strong generalization, advancing unsupervised 3D motion estimation in the event domain.