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

arXiv: https://arxiv.org/abs/2610.03283 · HTML: https://mlsanity.com/paper/2610.03283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 47 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [The TUM VI Benchmark for Evaluating Visual-Inertial Odometry](https://mlsanity.com/paper/1804.06120/) (2018)
- [Visual-Inertial Mapping with Non-Linear Factor Recovery](https://mlsanity.com/paper/1904.06504/) (2019)
- [HuB: Learning Extreme Humanoid Balance](https://mlsanity.com/paper/2505.07294/) (2025)
- [Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices](https://mlsanity.com/paper/2310.18329/) (2023)
- [Navion: A 2mW Fully Integrated Real-Time Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones](https://mlsanity.com/paper/1809.05780/) (2018)
- [Benchmarking Egocentric Visual-Inertial SLAM at City Scale](https://mlsanity.com/paper/2509.26639/) (2025)
- [Scaling LLM Test-Time Compute with Mobile NPU on Smartphones](https://mlsanity.com/paper/2509.23324/) (2025)
- [The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking](https://mlsanity.com/paper/2508.00088/) (2025)
- [eSLAM: An Energy-Efficient Accelerator for Real-Time ORB-SLAM on FPGA Platform](https://mlsanity.com/paper/1906.05096/) (2019)
- [Faster than FAST: GPU-Accelerated Frontend for High-Speed VIO](https://mlsanity.com/paper/2003.13493/) (2020)
- [Spatial Computing and Intuitive Interaction: Bringing Mixed Reality and Robotics Together](https://mlsanity.com/paper/2202.01493/) (2022)
- [From Virtual Reality to the Emerging Discipline of Perception Engineering](https://mlsanity.com/paper/2403.18588/) (2024)
- [High-Speed Stereo Visual SLAM for Low-Powered Computing Devices](https://mlsanity.com/paper/2410.04090/) (2024)
- [FastTrack: GPU-Accelerated Tracking for Visual SLAM](https://mlsanity.com/paper/2509.10757/) (2025)
- [GLidE-SLAM: GL-Accelerated Indirect-Direct Embedded SLAM](https://mlsanity.com/paper/2607.16897/) (2026)
- [The Impact and Outlook of 3D Gaussian Splatting](https://mlsanity.com/paper/2510.26694/) (2025)
- [LEVIO: Lightweight Embedded Visual Inertial Odometry for Resource-Constrained Devices](https://mlsanity.com/paper/2602.03294/) (2026)

## Abstract (arXiv)

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.