将事件相机数据压缩为离散神经事件，提升处理效率与精度
Neural Events: Discrete Asynchronous Autoencoders for Event-Based Vision
- 用可学习的离散编码重编码事件流，生成高信息密度的神经事件
- 在目标检测与分类任务中性能持平或超越现有方法，事件率降低2倍
- 适合需要高效处理事件流的实时视觉系统研发者
事件相机通过微秒级分辨率的连续事件流记录动态场景，但每个事件仅传递局部亮度变化的极低语义信息。下游算法需快速整合海量低信息事件以提取有意义信号，而现有架构常因难以平衡细粒度时间动态捕捉与数据吞吐量而受限。本文提出一种新框架，将事件流重新标记为少量高信息量的『神经事件』，每个神经事件代表一个局部时空上下文窗口，并由可学习的离散码表示。当该码发生变化时触发神经事件，从而生成高度压缩的数据流。实验表明，在目标检测与分类任务中，基于神经事件训练的模型性能达到或超过当前最先进方法，同时事件率降低2.0倍。
原文摘要 · Abstract (English)
Event cameras capture dynamic scenes with exceptional temporal fidelity by representing them as a continuous stream of microsecond resolution \textit{events}. Each individual event, however, only carries minimal semantic value, merely signaling a localized brightness change. To derive meaningful signals, downstream algorithms need to quickly integrate cues from a potentially massive torrent of low-information events. Current architectures, however, are easily overwhelmed, struggling to balance capturing fine-grained temporal dynamics and maintaining a manageable data throughput. This paper proposes a framework to re-tokenize event streams into a small set of highly informative \textit{neural events}, each representing a local spatio-temporal context window with a discrete learnable code. Every time this code flips, a neural event is triggered, yielding a highly compressed data stream. We demonstrate that, across object detection and classification, networks trained on neural events are on par or surpass the performance of state-of-the-art approaches while reducing the event rate by a factor of 2.0.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。