|国家预印本平台
首页|OmniEvent: Unified Event Representation Learning

OmniEvent: Unified Event Representation Learning

OmniEvent: Unified Event Representation Learning

来源:Arxiv_logoArxiv
英文摘要

Event cameras have gained increasing popularity in computer vision due to their ultra-high dynamic range and temporal resolution. However, event networks heavily rely on task-specific designs due to the unstructured data distribution and spatial-temporal (S-T) inhomogeneity, making it hard to reuse existing architectures for new tasks. We propose OmniEvent, the first unified event representation learning framework that achieves SOTA performance across diverse tasks, fully removing the need of task-specific designs. Unlike previous methods that treat event data as 3D point clouds with manually tuned S-T scaling weights, OmniEvent proposes a decouple-enhance-fuse paradigm, where the local feature aggregation and enhancement is done independently on the spatial and temporal domains to avoid inhomogeneity issues. Space-filling curves are applied to enable large receptive fields while improving memory and compute efficiency. The features from individual domains are then fused by attention to learn S-T interactions. The output of OmniEvent is a grid-shaped tensor, which enables standard vision models to process event data without architecture change. With a unified framework and similar hyper-parameters, OmniEvent out-performs (tasks-specific) SOTA by up to 68.2% across 3 representative tasks and 10 datasets (Fig.1). Code will be ready in https://github.com/Wickyan/OmniEvent .

Weiqi Yan、Chenlu Lin、Youbiao Wang、Zhipeng Cai、Xiuhong Lin、Yangyang Shi、Weiquan Liu、Yu Zang

计算技术、计算机技术电子技术应用自动化技术、自动化技术设备

Weiqi Yan,Chenlu Lin,Youbiao Wang,Zhipeng Cai,Xiuhong Lin,Yangyang Shi,Weiquan Liu,Yu Zang.OmniEvent: Unified Event Representation Learning[EB/OL].(2025-08-03)[2025-08-19].https://arxiv.org/abs/2508.01842.点此复制

评论