Video To Events: Recycling Video Datasets For Event Cameras
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)(2020)
摘要
Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with respect to conventional cameras: high dynamic range (HDR), high temporal resolution, and no motion blur. Recently, novel learning approaches operating on event data have achieved impressive results. Yet, these methods require a large amount of event data for training, which is hardly available due the novelty of event sensors in computer vision research. In this paper, we present a method that addresses these needs by converting any existing video dataset recorded with conventional cameras to synthetic event data. This unlocks the use of a virtually unlimited number of existing video datasets for training networks designed for real event data. We evaluate our method on two relevant vision tasks, i.e., object recognition and semantic segmentation, and show that models trained on synthetic events have several benefits: (i) they generalize well to real event data, even in scenarios where standard-camera images are blurry or overexposed, by inheriting the outstanding properties of event cameras; (ii) they can be used for fine-tuning on real data to improve over state-of-the-art for both classification and semantic segmentation.
更多查看译文
关键词
asynchronous events,event sensors,synthetic event data,event cameras,video datasets recycling,vision tasks,object recognition,semantic segmentation,high dynamic range,high temporal resolution,no motion blur,computer vision
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络