HexVIO: Towards All-Day Stereo-Inertial Tracking Through Commodity DSPs

2026-10-02

AI Summary

This study addresses the high power consumption and limited all-day real-time tracking capabilities of visual-inertial odometry (VIO) on mobile devices. For the first time, we efficiently deploy a stereo VIO visual frontend onto the Hexagon DSP of commercial smartphones. By leveraging heterogeneous computing architecture optimization and deeply fused visual-inertial algorithms, computationally intensive tasks are offloaded from the CPU to the DSP, effectively overcoming mobile bottlenecks in computational capacity and energy efficiency. Experimental results demonstrate that the proposed system achieves 30 fps real-time tracking at an exceptionally low power consumption of 0.83 W, reducing overall energy usage by 67% while improving throughput by 86%. This work provides a highly energy-efficient, round-the-clock localization solution for mobile platforms.

Abstract

The ability of a device to localize itself within its surroundings is a fundamental prerequisite for spatial computing. Visual-inertial odometry (VIO) has proven to be a cost-effective and accurate solution for this task. Robots, wearables, XR devices, and drones can benefit significantly from efficient implementations of VIO since they allow for cooler, lighter, and cheaper devices with longer battery life and a better user experience. In this work, we propose to enhance the efficiency of a VIO system by leveraging the Hexagon DSP, a commodity co-processor present in many modern smartphones and XR devices. Our approach offloads the visual frontend of a stereo-inertial odometry system to the DSP while keeping the backend on the main CPU. By optimizing the implementation for the DSP architecture, we achieve significant reductions in power consumption and latency compared to CPU-only execution. Our system, HexVIO, demonstrates a 67% reduction in power consumption or an 86% increase in throughput on a commodity smartphone, with the ability to sustain long-term real-time 30 fps tracking for 0.83 W, corresponding to ~18 hours of tracking on the testing device. These results highlight the potential of commodity DSPs for enabling all-day visual-inertial tracking in robotics and mobile devices.

Problem

• Visual-Inertial Odometry
• Power Consumption
• Latency
• Efficiency
• Spatial Computing

Innovation

• Visual-Inertial Odometry
• Hexagon DSP
• Stereo-Inertial Tracking
• Power Efficiency
• Hardware Offloading