用密集时间差特征提升事件流估计精度与效率
EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation
- 引入多尺度时序特征差注意力层，高效捕捉高分辨率运动模式
- 融合高低分辨率运动特征，提升细节表现与泛化能力
- 可作为插件模块增强现有方法，适合追求高分辨率流估计的场景
基于学习的事件流估计方法通常使用代价体进行像素匹配，但存在计算冗余且难以扩展至更高分辨率。本文提出轻量级事件流网络EDCFlow，利用相邻事件帧间密集时序特征差与代价体的互补性，实现高分辨率高质量流估计。具体地，设计了基于注意力的多尺度时序特征差层，在计算高效的同时捕捉多样运动模式；通过自适应融合高分辨率差分运动特征与低分辨率相关运动特征，增强运动表征并提升模型泛化性。值得注意的是，EDCFlow可作为即插即用模块，用于增强类似RAFT的事件流方法以获得更精细的流细节。大量实验表明，相较于现有方法，EDCFlow在更低复杂度下实现更优性能，具备更强泛化能力。
原文摘要 · Abstract (English)
Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to higher resolutions for flow refinement. In this work, we take advantage of the complementarity between temporally dense feature differences of adjacent event frames and cost volume and present a lightweight event-based optical flow network (EDCFlow) to achieve high-quality flow estimation at a higher resolution. Specifically, an attention-based multi-scale temporal feature difference layer is developed to capture diverse motion patterns at high resolution in a computation-efficient manner. An adaptive fusion of high-resolution difference motion features and low-resolution correlation motion features is performed to enhance motion representation and model generalization. Notably, EDCFlow can serve as a plug-and-play refinement module for RAFT-like event-based methods to enhance flow details. Extensive experiments demonstrate that EDCFlow achieves better performance with lower complexity compared to existing methods, offering superior generalization.
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。