POSTER
Beitong Tian, Lingzhi Zhao, Bo Chen, Mingyuan Wu, Haozhen Zheng, Deepak Vasisht, Francis Y. Yan, Klara Nahrstedt
Extreme environments, such as underwater settings, has constrained communication conditions including limited data rate and lossy channel which often requires specialized hardware. The state-of-the-art communication systems only support text messaging on mobile devices, severely limiting broader applications. We present AquaScope, the first communication system capable of underwater image transmission on commodity mobile devices. To address the key challenges of underwater environments -- limited bandwidth and high transmission errors -- AquaScope employs and enhances generative image compression to improve compression efficiency, and integrates it with reliability-enhancement techniques at the physical layer to strengthen error resilience. We implemented AquaScope on the Android platform and demonstrated its feasibility for underwater image transmission. Experimental results show that AquaScope enables reliable, low-latency image transmission while preserving perceptual image quality across various bandwidth-constrained and error-prone underwater conditions. We envision that the generative compression technique can be applied to a broader range of bandwidth-limited applications, such as AI-assisted AR systems in which smart glasses capture egocentric visual observations, offload them to an edge server for inference via bandwidth-limited uplink, and present returned guidance or responses to the user. More broadly, this capability can serve as a building block for immersive computing and communication systems, where rich visual context can be exchanged efficiently and reliably under stringent bandwidth and latency constraints.
AquaScope: Reliable Underwater Image Transmission on Mobile Devices