从对比到一致性：重新思考基于事件的连续时间光流估计
From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation
用时空结构一致性替代纯对比度最大化来约束事件相机光流，并给出从监督点约束到自监督流形正则的课程式混合训练流程，可直接迁移到事件相机或高帧率视频的连续运动估计。
原文依据 we propose a hybrid-supervised framework for continuous-time optical flow estimation, grounded in the principle of Spatio-temporal Structural Consistency
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论估计连续光流是动态视觉感知中一个基础而具有挑战性的问题。事件相机具有微秒级延迟和高动态范围，能够异步地捕捉亮度变化，为以精细时间精度建模运动提供了独特机会。然而，时间稠密真值标注的稀缺限制了监督学习的有效性；而以锐化扭曲事件图像（IWE）为核心的对比度最大化（CM）框架往往忽视时间连续性与结构一致性，在复杂运动下导致轨迹扭曲。为克服这些挑战，我们提出一种基于时空结构一致性（STSC）原理的连续时间光流估计混合监督框架。该范式同时约束局部结构稳定性与轨迹连续性，确保跨时间的物理一致运动。为进一步增强表征与鲁棒性，我们设计了双向互补的多尺度架构，并采用课程引导的混合训练策略，实现从监督点约束到自监督流形正则的平滑过渡。在多个基准上的综合实验表明，我们的方法在连续时间光流估计和标准光流估计上均达到最优性能，验证了所提学习范式的有效性。
英文原文摘要 1473 字符
Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique opportunity to model motion with fine temporal precision. However, the scarcity of temporally dense ground-truth annotations limits the effectiveness of supervised learning, while contrast maximization (CM) frameworks, focused on sharpening the Image of Warped Events (IWE), often neglect temporal continuity and structural coherence, leading to distorted trajectories under complex motion.To overcome these challenges, we propose a hybrid-supervised framework for continuous-time optical flow estimation, grounded in the principle of Spatio-temporal Structural Consistency (STSC). This paradigm jointly enforces local structural stability and trajectory continuity, ensuring physically coherent motion across time. To further enhance representation and robustness, we design a bidirectionally complementary multi-scale architecture and employ a curriculum-guided hybrid training strategy, enabling a smooth transition from supervised point constraints to self-supervised manifold regularization.Comprehensive experiments across multiple benchmarks show that our method achieves state-of-the-art performance in both continuous-time and standard optical flow estimation, demonstrating the effectiveness of the proposed learning paradigm.