SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields

TL;DR

SMF-VO introduces a lightweight, motion-centric visual odometry method that estimates velocities directly from sparse optical flow, enabling real-time performance on resource-limited devices without explicit pose or landmark tracking.

Contribution

The paper presents a novel sparse motion field framework for visual odometry that is computationally efficient and compatible with various camera models, including wide FOV lenses.

Findings

Achieves over 100 FPS on Raspberry Pi 5 using only CPU

Demonstrates superior efficiency compared to traditional pose-centric VO methods

Maintains competitive accuracy on benchmark datasets

Abstract

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.