用稀疏光流直接估速度，比传统方法更快更省资源
SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields
- 不求位姿、不建地图，直接从光流推运动速度
- 在树莓派5上仅用CPU实现超100帧/秒的实时性能
- 适合移动机器人和可穿戴设备等低算力场景
传统视觉里程计（VO）和视觉惯性里程计（VIO）采用‘位姿中心’范式，通过局部地图计算绝对相机位姿，需维护大规模特征点并持续优化地图，计算开销大，难以在资源受限设备上实时运行。为克服此问题，我们提出稀疏运动场视觉里程计（SMF-VO），一种轻量级的‘运动中心’框架。该方法直接从稀疏光流估计瞬时线速度与角速度，无需显式位姿估计或昂贵的特征点追踪。同时采用通用的基于3D射线的运动场建模，适用于多种相机模型，包括广角镜头。SMF-VO在基准数据集上表现出优异效率与竞争性精度，在树莓派5上仅使用CPU即可实现超过100帧/秒的性能。本工作为传统方法提供了可扩展且高效的替代方案，特别适用于移动机器人和可穿戴设备。
原文摘要 · Abstract (English)
Traditional Visual Odometry (VO) and Visual Inertial Odometry (VIO) methods rely on a 'pose-centric' paradigm, which computes absolute camera poses from the local map thus requires large-scale landmark maintenance and continuous map optimization. This approach is computationally expensive, limiting their real-time performance on resource-constrained devices. To overcome these limitations, we introduce Sparse Motion Field Visual Odometry (SMF-VO), a lightweight, 'motion-centric' framework. Our approach directly estimates instantaneous linear and angular velocity from sparse optical flow, bypassing the need for explicit pose estimation or expensive landmark tracking. We also employed a generalized 3D ray-based motion field formulation that works accurately with various camera models, including wide-field-of-view lenses. SMF-VO demonstrates superior efficiency and competitive accuracy on benchmark datasets, achieving over 100 FPS on a Raspberry Pi 5 using only a CPU. Our work establishes a scalable and efficient alternative to conventional methods, making it highly suitable for mobile robotics and wearable devices.
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。