Metraipolis › archive › dc_b4e9b4892fa5
On-Device Super-Resolution Imaging for a Low-Cost SPAD Array on a 640-KB-SRAM Microcontroller — arXiv:2610.09098
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09098
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T14:17:32.931Z
- SHA-256 of the archived text
fd3e9a21229b43f120521bb7442412220541661024eef043f0620ec43df62339- Stable URL of this page
https://metraipolis.com/documento/dc_b4e9b4892fa5
How to cite
On-Device Super-Resolution Imaging for a Low-Cost SPAD Array on a 640-KB-SRAM Microcontroller — arXiv:2610.09098 — arXiv (en), https://arxiv.org/abs/2610.09098 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b4e9b4892fa5 (Metraipolis archive dc_b4e9b4892fa5, sha256 fd3e9a21229b43f120521bb7442412220541661024eef043f0620ec43df62339)
BibTeX
@misc{dcb4e9b4892fa5,
title = {On-Device Super-Resolution Imaging for a Low-Cost SPAD Array on a 640-KB-SRAM Microcontroller — arXiv:2610.09098},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09098},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b4e9b4892fa5; sha256 fd3e9a21229b43f120521bb7442412220541661024eef043f0620ec43df62339},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09098. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This work presents a super-resolution (SR) deep-learning (DL) architecture to simultaneously upscale low-resolution (LR) depth and intensity images acquired by a consumer-grade VL53L9CX time-of-flight (ToF) sensor, a compact single-photon avalanche diode (SPAD) ranging device, while targeting deployment on a resource-constrained microcontroller (MCU) with only 640 KB SRAM and 2 MB Flash. The VL53L9CX provides 54 $\times$ 42 depth and intensity measurements. The proposed framework performs $\times$4 spatial SR to reconstruct 216 $\times$ 168 depth and intensity images simultaneously. The network employs separate reconstruction branches for intensity and high-resolution (HR) depth. We train the network with efficient loss functions and investigate the performance by testing multiple compact, hardware-oriented backbones, including Spatially Adaptive Feature Modulation (SAFM), Swift Parameter-Free Attention Network (SPAN), and Residual Local Feature Network (RLFN). We evaluate the network on both synthetic and real measurements, with particular attention to constrained activation and memory storage. We export the selected network to ONNX, quantize it to INT8, generate C inference code for an STM32H563ZI Arm Cortex-M33 MCU, and integrate it with our simplified sensor's firmware. This work is the first to demonstrate a compact DL SR model on a low-cost bare-metal MCU for a consumer-grade LR SPAD sensor, integrated with customized MCU firmware to enable on-device SR inference. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv eess.IV, nuovi lavori del giorno). Categorie arXiv: Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2610.09098 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:29:15.726Z dalla pagina https://arxiv.org/list/eess.IV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).