BlinkFlow: A Dataset to Push the Limits of Event-based Optical Flow Estimation

TL;DR

This paper introduces BlinkSim, a fast simulator for generating large-scale, diverse event-based optical flow data, and demonstrates its effectiveness in improving the generalization of optical flow estimation methods.

Contribution

The paper presents BlinkSim, a novel simulator for large-scale event data generation, and a new dataset BlinkFlow, enhancing training and evaluation for event-based optical flow estimation.

Findings

BlinkFlow improves generalization of state-of-the-art methods by over 40%.

E-FlowFormer outperforms SOTA by up to 91% on MVSEC.

The dataset enables robust training and evaluation of event-based optical flow models.

Abstract

Event cameras provide high temporal precision, low data rates, and high dynamic range visual perception, which are well-suited for optical flow estimation. While data-driven optical flow estimation has obtained great success in RGB cameras, its generalization performance is seriously hindered in event cameras mainly due to the limited and biased training data. In this paper, we present a novel simulator, BlinkSim, for the fast generation of large-scale data for event-based optical flow. BlinkSim incorporates a configurable rendering engine alongside an event simulation suite. By leveraging the wealth of current 3D assets, the rendering engine enables us to automatically build up thousands of scenes with different objects, textures, and motion patterns and render very high-frequency images for realistic event data simulation. Based on BlinkSim, we construct a large training dataset and evaluation benchmark BlinkFlow that contains sufficient, diversiform, and challenging event data with optical flow ground truth. Experiments show that BlinkFlow improves the generalization performance of state-of-the-art methods by more than 40\% on average and up to 90\%. Moreover, we further propose an Event-based optical Flow transFormer (E-FlowFormer) architecture. Powered by our BlinkFlow, E-FlowFormer outperforms the SOTA methods by up to 91\% on the MVSEC dataset and 14\% on the DSEC dataset and presents the best generalization performance. The source code and data are available at https://zju3dv.github.io/blinkflow/.