Jiangning Zhang ^1,*,✉ ,  Haojun Chen ^1,* ,  Yong Liu ¹

¹Zhejiang University, APRIL Lab

This repository accompanies our survey From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms and maintains a structured collection of smart-glasses products/platforms, foundational capabilities, and application scenarios, which will be continuously updated.For more details, kindly refer to our paper 🚀

💬 Researchers and industry practitioners are welcome to join our WeChat group; we look forward to exchanging ideas and collaborating with you.

📰 News

• 2026-08-26: We release our initial-version survey: From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms.

Table of Contents

• 🎯 Contributions
• 👓 Representative Smart-Glasses Products/Platforms
• 📏 Foundational Capabilities for Smart Glasses
• 🌍 Application Scenes for Smart Glasses
  • 4.1 Daily Situated Assistance
  • 4.2 Accessibility Assistance
  • 4.3 Industrial Workflow Support
  • 4.4 Healthcare and Caregiving
  • 4.5 Education and Skills Training
  • 4.6 Mobility and Transportation Safety
  • 4.7 Social Interaction and Collaboration
  • 4.8 Spatial Intelligence
  • 4.9 Embodied Intelligence
• 📄 Citation
• 🤝 Contributing
• 🔗 Related Resources & Links
• 🤗 Acknowledgments

🎯 Contributions

1️⃣ A formal and hardware-grounded problem definition.

We define smart glasses through a first-person observation stream, a closed-loop mapping from observation and intent to feedback, persistent state, and optional action, and a constrained utility objective that makes latency, energy, thermals, privacy, and social cost explicit. We further consolidate heterogeneous devices into eight verifiable hardware capability axes and route-aware product profiles, converting marketing categories into evidence-bearing experimental substrates.

2️⃣ A compositional capability framework with explicit evidential boundaries.

We synthesize seven interdependent capabilities: first-person perception, multimodal context, persistent spatial state, auditable personal memory, situated agentic action, embodied data interfaces, and cross-cutting deployment constraints. Building upon these building blocks, we present an L0-L5 framework that covers capture, reactive perception, contextual assistance, persistent state, governed action, and embodied coupling. The framework treats levels as task- and evidence-conditioned claims, distinguishes prerequisites from demonstrated capability, and makes clear that L5 crosses the embodiment boundary rather than simply extending the wearer-facing L0-L4 axis.

3️⃣ An application-centered evidence map.

We reorganize the literature into nine application scenes and connect each scene to its required capability loop, representative datasets and benchmarks, research systems, product entry points, affected stakeholders, failure consequences, and missing validation evidence. This structure separates transferable component evidence from direct smart-glasses evidence and clarifies why identical model functions require different thresholds in daily assistance, accessibility, industry, healthcare, education, mobility, social collaboration, spatial intelligence, and embodied intelligence.

4️⃣ A deployment and evaluation blueprint.

We formulate nine coupled design dimensions covering hardware, runtime, perception and inference, memory, feedback, external action, reliability, governance, and reproducibility. On this basis, we provide a claim-conditioned evaluation protocol, a deployment checklist, and an iterative evidence ladder that connects documentation, laboratory measurement, benchmark testing, device-stream replay, fault injection, end-to-end studies, longitudinal deployment, and privacy or security audit. We finally derive eight open challenges and six roadmap directions for building trustworthy first-person embodied-intelligence systems.

Representative Smart-Glasses Products/Platforms

👓 The table below summarizes some representative smart-glasses products/platforms and their corresponding links (⏰ last update: 2026.09.06).

Figure: Hardware stack and hardware-based capability-axis consolidation.

Foundational Capabilities for Smart Glasses

Figure: Foundational capabilities and L0-L5 cross-capability level framework.

⏰ We organize the works in chronological order, from the latest to the earliest. 🎨 Colored labels indicate seven foundational capabilities to which the work contributes: , , , , , , and .

Application Scenes for Smart Glasses

⏰ For each application scene, we organize the works in chronological order, from the earliest to the latest.

4.1 Daily Situated Assistance

4.2 Accessibility Assistance

4.3 Industrial Workflow Support

4.4 Healthcare and Caregiving

4.5 Education and Skills Training

4.6 Mobility and Transportation Safety

4.7 Social Interaction and Collaboration

4.8 Spatial Intelligence

4.9 Embodied Intelligence

📄 Citation

If you find our work helpful, please consider citing our paper:

@misc{zhang2026seeingactingsmartglasses,
      title={From Seeing to Acting: Smart Glasses as First-Person Intelligence Platforms}, 
      author={Jiangning Zhang and Haojun Chen and Yong Liu},
      year={2026},
      eprint={2608.24877},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2608.24877}, 
}

🤝 Contributing

Contributions are welcome. Please open an issue or submit a pull request to add or correct related smart-glasses products/platforms and works (datasets, benchmarks, methods, systems, and application resources). New entries should include a verifiable paper, official product/project page, or repository link.

🔗 Related Resources & Links

• Awesome Egocentric Vision
• Awsome Ego Equipments
• An open smart-glasses product and market dataset
• MentraOS

🤗 Acknowledgments

We thank the authors, dataset and benchmark creators, product and platform developers, and open-source contributors whose work supports this survey.

---