面向事件相机运动分割的运动边界归属
Moving Border Ownership for Event-based Motion Segmentation
把运动分割重新表述为「运动边界归属」预测：用有符号距离场编码边界朝向与前景归属，并以 Blender 合成事件提供完美监督，使模型在真实事件数据集上零样本迁移；这一「边界归属场 + 合成监督」思路可迁移到事件相机上的光流、遮挡推理与目标分割。
原文依据 trained on synthetic events, it achieves zero-shot transfer on EED, EVIMO1, EVIMO2, and EMSMC
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论事件相机在运动边界处提供精确信息——正是在这些位置，解耦自运动、物体运动与边界归属决定了分割质量。我们认为，动态场景理解中缺失的关键要素是运动边界归属：检测运动边界并判定哪一侧是前景，从而在设计上解决遮挡问题。传统的几何运动分割流程（如光流聚类、简单运动模型）仍然依赖大量假设且速度慢，而深度模型往往难以跨传感器或跨数据集泛化。我们提出一种轻量级、具备归属感知的预测器，仅使用通过 Blender 流程生成的、对边界、归属与运动具有完美监督的合成事件进行训练。其关键目标——有符号距离归属场与运动掩码——将学习集中在事件发生的位置，并产生稳定的梯度。该模型可实时运行且无需调参即可泛化：在合成事件上训练后，它在 EED、EVIMO1、EVIMO2 和 EMSMC 上实现零样本迁移，达到最优性能。通过将运动分割转化为归属感知的边缘理解，我们将基于模型推理的鲁棒性与学习的可扩展性结合起来。
英文原文摘要 1248 字符
Event cameras provide accurate information at motion boundaries--exactly where disentangling ego-motion, object motion, and border ownership determines segmentation quality. We argue that the missing ingredient in dynamic scene interpretation is moving border ownership: detecting motion boundaries and assigning which side is foreground so occlusions are resolved by design. Traditional geometric motion segmentation pipelines (e.g., flow clustering, simple motion models) remain assumption-heavy and slow, while deep models often fail to generalize across sensors or datasets. We introduce a lightweight, ownership-aware predictor trained solely on synthetic events with perfect supervision for boundaries, ownership, and motion, generated via a Blender pipeline. Its key targets--a signed-distance ownership field and a motion mask--focus learning where events occur and yield stable gradients. The model runs in real time and generalizes without tuning: trained on synthetic events, it achieves zero-shot transfer on EED, EVIMO1, EVIMO2, and EMSMC, delivering state-of-the-art performance. By casting motion segmentation as ownership-aware edge understanding, we combine the robustness of model-based reasoning with the scalability of learning.