Work

Deep learning-enhanced super-resolution imaging using low-cost single photon avalanche diodes

Year: 2025

Type: article

Abstract: This study presents a non-fusion super-resolution (SR) solution to enhance the performance of low-cost, consumer-grade single-photon avalanche diode (SPAD) arrays. We present a compact deep learning (DL) model that takes low-resolution (LR, 8 × 8) depth and intensity inputs and simultaneously reconstructs high-resolution (HR, 50 × 50) images. The model was evaluated on synthetic datasets spanning diverse scenes and real measurements from an STMicroelectronics VL53L8CX SPAD array. Results show high fidelity against ground truth images for synthetic datasets, and more precise structural details in real datasets. To facilitate hardware deployment, the model was further compressed using INT8 quantization, resulting in only a marginal loss in accuracy. Both the original and quantized models achieve video-rate SR reconstruction on a mid-range GPU. Owing to its compact size, the DL model is well-suited to modern edge-computing platforms and offers strong potential for mobile and embedded applications.

Source: Optics Express

DOI: 10.1364/oe.580789

Authors: Zhenya Zang, Xingda Li, David Day-Uei Li

Language: English

Topic: Advanced Image Processing Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,270

Funders: Engineering and Physical Sciences Research Council, Innovate UK

Awards: QuantIC - The UK Quantum Technology Hub in Quantum Imaging, HYDRI - HYDrogen sensoR for Industry