On-Device Super Resolution Imaging Using Low-Cost SPAD Array and Embedded Lightweight Deep Learning
It addresses the need for cost-effective, high-resolution depth and intensity imaging from low-resolution consumer-grade SPAD sensors for embedded applications.
This paper presents a lightweight super-resolution neural network (LiteSR) that enhances 48x32 SPAD array images to 256x256 (and up to 512x512) resolution, achieving real-time video streaming on an Arduino UNO Q microcontroller. The method demonstrates high reconstruction fidelity on synthetic and real datasets, including noise-corrupted inputs.
This work presents a lightweight super-resolution (LiteSR) neural network for depth and intensity images acquired from a consumer-grade single-photon avalanche diode (SPAD) array with a 48x32 spatial resolution. The proposed framework reconstructs high-resolution (HR) images of size 256x256. Both synthetic and real datasets are used for performance evaluation. Extensive quantitative metrics demonstrate high reconstruction fidelity on synthetic datasets, while experiments on real indoor and outdoor measurements further confirm the robustness of the proposed approach. Moreover, the SPAD sensor is interfaced with an Arduino UNO Q microcontroller, which receives low-resolution (LR) depth and intensity images and feeds them into a compressed, pre-trained deep learning (DL) model, enabling real-time SR video streaming. In addition to the 256x256 setting, a range of target HR resolutions is evaluated to determine the maximum achievable upscaling resolution (512x512) with LiteSR, including scenarios with noise-corrupted LR inputs. The proposed LiteSR-embedded system co-design provides a scalable, cost-effective solution to enhance the spatial resolution of current consumer-grade SPAD arrays to meet HR imaging requirements.