VueBuds: Earbuds with Rice-Sized Cameras Enable AI Visual Queries
At the University of Washington, a team of researchers has introduced VueBuds, a prototype that incorporates miniature cameras into wireless earbuds. These cameras, comparable in size to a grain of rice, produce low-resolution grayscale images that are transmitted to a connected smartphone via Bluetooth for processing. Users can inquire about their environment, such as asking for text translations. Instead of streaming video, the system captures still images to manage bandwidth limitations. A light signals when an image is taken, which can be deleted by the user. The cameras feature a field of view ranging from 98 to 108 degrees, with a blind spot for objects closer than 7.8 inches. Lead author Maruchi Kim and senior author Shyam Gollakota emphasized the advantages of earbuds over smart glasses, with potential future iterations possibly including color cameras.
Key facts
- VueBuds integrate tiny cameras into off-the-shelf wireless earbuds.
- Cameras are the size of a grain of rice.
- Images are low-resolution grayscale.
- Processing occurs locally on a paired device via Bluetooth.
- Users can ask AI questions about their surroundings, e.g., translating text.
- A light indicates when images are captured; users can delete them immediately.
- Cameras are tilted 5–10 degrees outward for a 98–108 degree field of view.
- Blind spot only for objects closer than 7.8 inches.
- Lead author: Maruchi Kim (doctoral student at Paul G. Allen School).
- Senior author: Shyam Gollakota.
- System avoids video streaming due to Bluetooth and power constraints.
- Future versions may add color cameras or specialized AI models.
- Development follows reports of Apple planning camera-equipped AirPods.
- Apple's AirPods cameras are for contextual AI, not photo/video capture.
Entities
Institutions
- University of Washington
- Paul G. Allen School of Computer Science & Engineering
- Apple
- Meta
Locations
- Seattle
- United States