paper-with-me

Papers

OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance

2026-07-03 · Mengzhang Li, Yuan Yao arxiv

We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind and low-vision users. Cloud MLLM assistants offer strong visual understanding, but often require uploading first-person visual data and can suffer multi-second network delays; wearable glasses are ideal for sensing, but cannot host large models under tight compute and power budgets. OpenGlass addresses this gap with a sensing-computing split: an ESP32-based glasses-side unit captures visual context, while a nearby consumer-grade device performs local MLLM inference and local speech output, reducing cloud reliance and keeping raw egocentric visual data on user-controlled devices by default. We evaluate response quality, query-ready-to-audio latency, safety-aware abstention, and auditable logs. Under real ESP32 Wi-Fi capture, OpenGlass reaches 993 ms median user-to-audio latency with resized payloads and 1625 ms with raw 1280 x 720 payloads; 97.5% and 93.3% of trials fall below 2 s, respectively. OpenGlass is a user-initiated visual-assistance reference platform for obstacle/hazard awareness, sign/object queries, and image-quality self-checking, rather than a certified navigation aid. We release source code, hardware instructions, prompts, evaluation data, and logs.

📄 PDF Abstract BibTeX arXiv:2607.03213

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons

2025-06-24 · Dengyu Wu, Jiechen Chen, H. Vincent Poor, Bipin Rajendran 외

Neuromorphic computing offers an energy-efficient alternative to conventional deep learning accelerators for real-time time-series processing. However, many edge applications, such as wireless sensing and audio recogniti…

Audio Classification

Neuromorphic Split Computing with Wake-Up Radios: Architecture and Design via Digital Twinning

2024-04-02 · Jiechen Chen, Sangwoo Park, Petar Popovski, H. Vincent Poor 외

Neuromorphic computing leverages the sparsity of temporal data to reduce processing energy by activating a small subset of neurons and synapses at each time step. When deployed for split computing in edge-based systems, …

Informativeness

MTL-Split: Multi-Task Learning for Edge Devices using Split Computing

2024-07-08 · Luigi Capogrosso, Enrico Fraccaroli, Samarjit Chakraborty, Franco Fummi 외

Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs…

Multi-Task Learning

Neural Architecture Search for Improving Latency-Accuracy Trade-off in Split Computing

2022-08-30 · Shoma Shimizu, Takayuki Nishio, Shota Saito, Yoichi Hirose 외

This paper proposes a neural architecture search (NAS) method for split computing. Split computing is an emerging machine-learning inference technique that addresses the privacy and latency challenges of deploying deep l…

Neural Architecture Search

Edge Information Hub: Orchestrating Satellites, UAVs, MEC, Sensing and Communications for 6G Closed-Loop Controls

2024-03-11 · Chengleyang Lei, Wei Feng, Peng Wei, Yunfei Chen 외

An increasing number of field robots would be used for mission-critical tasks in remote or post-disaster areas. Due to the limited individual abilities, these robots usually require an edge information hub (EIH), with no…

Edge-computing