We study the problem of estimating optical flow from event cameras. One important issue is how to build a high-quality event-flow dataset with accurate event values and flow labels. Previous datasets are created by either capturing real scenes by event cameras or synthesizing from images with pasted foreground objects. The former case can produce real event values but with calculated flow labels, which are sparse and inaccurate. The later case can generate dense flow labels but the interpolated events are prone to errors. In this work, we propose to render a physically correct event-flow dataset using computer graphics models. In particular, we first create indoor and outdoor 3D scenes by Blender with rich scene content variations. Second, diverse camera motions are included for the virtual capturing, producing images and accurate flow labels. Third, we render high-framerate videos between images for accurate events. The rendered dataset can adjust the density of events, based on which we further introduce an adaptive density module (ADM). Experiments show that our proposed dataset can facilitate event-flow learning, whereas previous approaches when trained on our dataset can improve their performances constantly by a relatively large margin. In addition, event-flow pipelines when equipped with our ADM can further improve performances.

翻译：我们研究从事件相机估计光流的问题。其中一个关键问题是如何构建具有精确事件值和光流标签的高质量事件-光流数据集。以往的数据集要么通过事件相机捕捉真实场景生成，要么从带有粘贴前景物体的图像合成得到。前者可以产生真实事件值，但计算得到的光流标签稀疏且不精确；后者可以生成稠密光流标签，但插值事件容易产生误差。本文提出利用计算机图形模型渲染物理正确的事件-光流数据集。具体而言，我们首先通过Blender创建包含丰富场景内容变化的室内外3D场景；其次，虚拟捕捉过程中包含多样相机运动，生成图像和精确光流标签；最后，渲染图像间的高帧率视频以获得精确事件。该渲染数据集可调节事件密度，并据此进一步引入自适应密度模块（ADM）。实验表明，我们提出的数据集能够促进事件-光流学习，而以往方法在基于该数据集训练时，其性能能够持续获得较大幅提升。此外，配备ADM的事件-光流管线可进一步提升性能。