E-WAVE: Event-based Continuous Optical Flow via Warping-Aligned Visual Encoding

2026-09-28

AI Summary

This study addresses the challenge of balancing high temporal resolution with computational efficiency in event-based optical flow estimation for VR/AR applications, as well as the prohibitive memory overhead of conventional correlation volumes. We propose a correlation-free continuous optical flow estimation framework that leverages global attention mechanisms to model long-range dependencies. Furthermore, we introduce a novel Bézier curve-guided feature warping mechanism to replace exhaustive pairwise correlation volume construction, enabling efficient querying of flow trajectories at arbitrary timestamps following a single inference pass. Experiments demonstrate that our framework reduces trajectory errors by 25% on the MultiFlow and DSEC-Flow benchmarks while achieving accuracy comparable to state-of-the-art methods. Additionally, real-world evaluations on head-mounted devices exhibit strong robustness, confirming its practical viability for immersive applications.

Abstract

Temporally dense optical flow is essential for dynamic perception in immersive VR/AR systems, where rapid head, hand, and object motion must be continuously captured and tracked. Existing frame-based optical flow estimation methods are constrained by the tradeoff between temporal resolution and computational cost; while event cameras, with their high temporal resolution and energy efficiency, serve as a natural solution to the dilemma. However, event-based approaches commonly rely on correlation volumes to capture pairwise voxel correspondences, which incur substantial memory and computation overhead. We present E-WAVE, a correlation-free framework for high-temporal-resolution (HTR) optical flow estimation from event streams. Instead of constructing all-pairs correlation volumes, E-WAVE employs global attention mechanism to model long-range feature dependencies and performs trajectory guided feature warping using Bézier curve. Through iterative updates, it predicts trajectories that allow for querying at arbitrary timestamps without repeated inference. Experiments on MultiFlow and DSEC-Flow demonstrate a 25% lower trajectory error and comparable endpoint flow estimation accuracy relative to state-of-the art baselines. Additional evaluations on self-captured data using a head-mounted prototype validate that E-WAVE remains robust under challenging real-world conditions.

Problem

• optical flow estimation
• event camera
• high temporal resolution
• correlation-free
• VR/AR

Innovation

• Event-based Optical Flow
• Correlation-free Framework
• Global Attention Mechanism
• Bézier Curve Warping
• Continuous Trajectory Prediction