arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.15465cs.CV
收藏

从神经形态数据中动态重建

Dynamic Reconstruction from Neuromorphic Data

George Mason University(乔治梅森大学)

Harbir Antil, Daniel Blauvelt, David Sayre

AI总结:

针对仅依赖神经形态事件数据重建图像与动态的难题,本文提出一种基于优化的逐像素时间建模方法,无需额外信息即可实现高效准确的重建。

摘要:

与传统相机同步记录像素强度不同,神经形态传感器仅在发生变化的像素上异步记录“变化”。这使得神经形态传感器能够以微秒级进行采样并高效捕捉动态信息。由于记录的仅是异步事件变化的序列,而非随时间变化的亮度强度,许多传统图像处理技术无法直接应用。此外,包括作者最近提出的方法在内的现有方法,均使用传统图像结合神经形态事件数据来进行重建。本工作的目标是引入一种基于优化的方法,仅从神经形态事件数据重建图像和动态,而无需任何关于事件的额外知识。每个像素在时间维度上被建模。在真实数据上的实验结果突显了该方法的有效性,为在真实世界应用中高效准确地处理神经形态传感器数据铺平了道路。

英文摘要:

Unlike traditional cameras which synchronously register pixel intensity, neuromorphic sensors only register `changes' at pixels where a change is occurring asynchronously. This enables neuromorphic sensors to sample at a micro-second level and efficiently capture the dynamics. Since, only sequences of asynchronous event changes are recorded rather than brightness intensities over time, many traditional image processing techniques cannot be directly applied. Furthermore, existing approaches, including the ones recently introduced by the authors, use traditional images combined with neuromorphic event data to carry out reconstructions. The aim of this work is introduce an optimization based approach to reconstruct images and dynamics only from the neuromoprhic event data without any additional knowledge of the events. Each pixel is modeled temporally. The experimental results on real data highlight the efficacy of the presented approach, paving the way for efficient and accurate processing of neuromorphic sensor data in real-world applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑