发表机构
KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于事件相机的特征跟踪问题，提出用强化学习框架自适应控制事件累积过程，训练智能体依运动线索决策，引入新数据集评估，集成该框架到现有方法可提升性能，在动态运动下更具鲁棒性且平衡跟踪精度与效率。
AI 中文摘要
特征跟踪在理解场景运动中起着基础性作用，并支持各种下游任务。事件相机具有高时间分辨率和异步传感能力，适用于快速和非线性运动下的特征跟踪。然而，现有基于事件的特征跟踪方法依赖于基于手动调整的固定启发式规则进行事件累积，无法适应多样的运动动态。本文将事件累积建模为顺序决策问题，引入强化学习框架来自适应控制基于事件的在线特征跟踪的累积过程，并训练一个强化学习智能体根据运动线索决定是否继续累积事件或进行跟踪推理。此外，引入了具有动态运动分布的动态事件跟踪（DEFT）数据集来评估特征跟踪的鲁棒性。实验表明，将该即插即用框架集成到现有特征跟踪方法中始终优于基于启发式的方法，在动态运动下提高了鲁棒性，同时在跟踪准确性和效率之间取得了更好的平衡。
英文摘要
Feature tracking plays a fundamental role in understanding scene motion and supports various downstream tasks. Event cameras, with their high temporal resolution and asynchronous sensing, enable low-latency and motion-robust perception, making them well-suited for feature tracking under fast and non-linear motion. However, existing event-based feature tracking methods rely on fixed heuristic rules based on hand-tuning for event accumulation. Such strategies fail to adapt to diverse motion dynamics, leading to degraded performance under abrupt motion changes or low-motion scenarios. In this paper, we model event accumulation as a sequential decision-making problem and introduce reinforcement learning (RL) framework to adaptively control the accumulation process for online event-based feature tracking. Our approach trains a RL agent that decides whether to continue accumulating events or to perform tracking inference based on motion cues. The proposed adaptive temporal agent enables dynamic adaptation to varying motion patterns without relying on hand-crafted rules. Furthermore, we introduce a Dynamic Event-based Tracking (DEFT) dataset with dynamic motion distributions to evaluate the robustness of the feature tracking. Extensive experiments demonstrate that integrating our plug-and-play framework to existing feature tracking methods consistently outperforms heuristic-based approaches, improving robustness under dynamic motion while offering a better balance between tracking accuracy and efficiency. Our project codes and datasets are available at https://github.com/kmax2001/GoSTOP
CommentsAccepted to ECCV 2026
