From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation
2026-05-25 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of estimating smooth motion (optical flow) using event-based cameras, which capture changes very quickly but lack detailed labeled data for training. They introduce a new method that combines supervised learning with self-supervised techniques to maintain consistent motion paths over time. Their approach uses a special structure to keep motion physically realistic and smooth. Experiments show their method works better than previous ones for continuous-time flow estimation.
optical flowevent-based camerascontinuous-time estimationcontrast maximizationImage of Warped Events (IWE)spatio-temporal consistencyhybrid-supervised learningself-supervised learningmulti-scale architecture
Authors
Rui Hu, Song Wu, Wen Yang, Jinjian Wu
Abstract
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.