SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields
This provides a scalable and efficient alternative for mobile robotics and wearable devices, though it is incremental as it builds on existing motion field concepts.
The paper tackled the computational expense of traditional visual odometry methods by introducing SMF-VO, a lightweight framework that directly estimates camera motion from sparse optical flow, achieving over 100 FPS on a Raspberry Pi 5 with competitive accuracy.
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.