arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.04500cs.CVcs.AI
收藏

ReynoldsFlow:用于视频理解的物理启发式时空流表示

ReynoldsFlow: Physics-Inspired Spatiotemporal Flow Representation for Video Understanding

The University of Melbourne(墨尔本大学);National Yang Ming Chiao Tung University(国立阳明交通大学)

Yu-Hsi Chen, Ching-Kai Lin, PingKong Huang, Chin-Tien Wu

AI总结:

针对现有视频理解方法计算成本高、运动表示鲁棒性差的问题,提出基于RTT和HHD的ReynoldsFlow,分解运动为CF和DF分量,可提升下游任务性能且兼具轻量高效性。

摘要:

视频理解目前主要依赖深度时空架构,包括3D卷积网络和基于光流(OF)的模型。这些方法虽有效,但通常计算成本高昂,且依赖对光照、尺度和结构变化敏感的启发式运动表示。为解决这些局限,我们提出ReynoldsFlow,一种基于雷诺输运定理(RTT)和亥姆霍兹-霍奇分解(HHD)的物理启发式表示。ReynoldsFlow将运动分解为无旋(CF)和无散(DF)分量,为场景动态提供有原则且可解释的表征。通过将强度信息与分解后的运动线索结合,它生成感知动态、保留纹理的特征,可提升姿态估计、动作识别和微小物体检测等下游任务的性能。ReynoldsFlow轻量且模块化,可轻松集成到现有架构中。在不同基准上的实验表明,ReynoldsFlow始终能达到或超越现有方法,具备更好的泛化性和计算效率。

英文摘要:

Video understanding has largely relied on deep spatiotemporal architectures, including 3D convolutional networks and optical flow (OF) based models. While effective, these methods are often computationally expensive and depend on heuristic motion representations that are sensitive to illumination, scale, and structural changes. To address these limitations, we propose ReynoldsFlow, a physics-inspired representation grounded in the Reynolds transport theorem (RTT) and Helmholtz-Hodge decomposition (HHD). ReynoldsFlow decomposes motion into curl-free (CF) and divergence-free (DF) components, providing a principled and interpretable characterization of scene dynamics. By coupling intensity information with decomposed motion cues, it produces dynamics-aware, texture-preserving features that boost downstream tasks such as pose estimation, action recognition, and tiny object detection. Lightweight and modular, ReynoldsFlow can be readily integrated into existing architectures. Experiments across diverse benchmarks show that ReynoldsFlow consistently matches or surpasses existing approaches, offering improved generalizability and computational efficiency.

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。

↑