Conventional embedded cameras capture only visible light and spend most of their energy on the image sensor and on streaming pixels. PixelGen instead senses the environment with a handful of low-power sensors, including audio, magnetic and other modalities, and transmits that compact description at a fraction of the energy. A multimodal generative model on the receiving side reconstructs a rich visual representation, which can be viewed on a mixed-reality headset.
PixelGen was published at the ImmerCom workshop at MobiCom ‘24, and its demonstration received the Best Demo Runner-Up award at IPSN ‘24.
Publications
PixelGen: Rethinking Embedded Cameras for Mixed-Reality
Kunjun Li*, Manoj Gulati*, Dhairya Shah*, Steven Waskito, Shantanu Chakrabarty, and Ambuj Varshney
@inproceedings{pixelgen_mobicom24,author={Li, Kunjun and Gulati, Manoj and Shah, Dhairya and Waskito, Steven and Chakrabarty, Shantanu and Varshney, Ambuj},title={PixelGen: Rethinking Embedded Cameras for Mixed-Reality},year={2024},isbn={9798400704895},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3636534.3696216},doi={10.1145/3636534.3696216},booktitle={Proceedings of the 30th Annual International Conference on Mobile Computing and Networking (MobiCom '24)},pages={2128–2135},numpages={8},keywords={embedded systems, networking, large language models},location={Washington D.C., DC, USA},series={ACM ImmerCom (MobiCom) '24}}
Demo Abstract: PixelGen: Rethinking Embedded Camera Systems for Mixed-Reality
Kunjun Li*, Manoj Gulati*, Dhairya Shah, Steven Waskito, Shantanu Chakrabarty, and Ambuj Varshney
@inproceedings{pixelgen_ipsn24demo,author={Li, Kunjun and Gulati, Manoj and Shah, Dhairya and Waskito, Steven and Chakrabarty, Shantanu and Varshney, Ambuj},booktitle={2024 23rd ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)},title={Demo Abstract: PixelGen: Rethinking Embedded Camera Systems for Mixed-Reality},year={2024},volume={},number={},pages={271-272},series={ACM/IEEE IPSN '24},keywords={Headphones;Visualization;Power demand;Magnetic sensors;Mixed reality;Virtual reality;Sensor phenomena and characterization;Embedded Camera Systems;Mixed Reality;Multimodal AI;Low-power Systems},doi={10.1109/IPSN61024.2024.00036}}