RealSense-Event-Sim

An Intel RealSense depth sensor is first used to capture 119 infrared video sequences at a resolution of 640×480, covering variations in velocity, lighting conditions, and scene diversity. These videos are then converted into event streams using the V2E simulator. The synthetic dataset provides stereo event streams along with 23.8k synchronized labels. We split the dataset into 16k samples for training, 3.8k for validation, and 4k for testing.本数据集首先采用英特尔实感（Intel RealSense）深度传感器采集119段红外视频序列，分辨率为640×480，涵盖速度、光照条件与场景多样性的各类变化。随后通过V2E模拟器将上述视频转换为事件流。该合成数据集提供立体事件流与23.8k个同步标注标签。我们将数据集划分为16k个训练样本、3.8k个验证样本与4k个测试样本。

搜集汇总

背景与挑战

背景概述

RealSense-Event-Sim数据集由jianingli创建，采用Apache License 2.0许可证，大小约为94.81GB，于2026年5月11日更新。该数据集以压缩文件形式提供，需通过cat命令合并三个分割部分以还原完整文件。