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 consists of a configurable rendering engine and a flexible engine for event data simulation. 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 optical Flow transFormer (E-FlowFormer) architecture. Powered by our BlinkFlow, E-FlowFormer outperforms the SOTA methods by up to 91% on MVSEC dataset and 14% on DSEC dataset and presents the best generalization performance.
翻译:事件相机提供高时间精确度、低数据率和高动态范围视觉感知,这些都非常适合光学流量估计。虽然数据驱动光学流量估计在 RGB 相机中取得了巨大成功,但其一般性能在事件相机中受到严重阻碍,主要原因是培训数据有限和偏差。在本文中,我们展示了一个新的模拟器BlinkSim,用于快速生成基于事件光学流的大型数据。BlinkSim 包含一个可配置的成像引擎和一个灵活的事件模拟数据引擎。通过利用现有3D资产的财富,数据引擎使我们能够用不同的对象、纹理和运动模式自动建立数千场场景,并为现实事件数据模拟提供非常高频的图像。在BlinkSim的基础上,我们建立了一个大型的培训数据集和评价基准BlinkFlow, 其中包含充分、 下潜化和具有挑战性的光学流地面数据。 实验显示,BlinkFlow改进了当前3D资产的通用化性能。在普通和光学中,我们用40 %以上的时间和光学F 展示了常规数据,然后是SIRF 。</s>