arXiv · 2611.12980
MADSNet: A Multi-Scale Axial-Attentive Dense Spiking Network for Spike Camera Image Reconstruction
Abstract
Spike cameras encode dynamic scenes into high-temporal-resolution binary spike streams for efficient high-speed vision. Although spiking neural networks (SNNs) can process such signals with sparse and accumulate-only computation, existing SNN-based reconstruction methods are typically shallow and still lag behind ANN-based models in reconstruction fidelity. This paper proposes MADSNet, a Multi-scale Axial-attentive Dense Spiking Network for spike camera image reconstruction. MADSNet adopts a hierarchical spiking encoder--decoder, where a multi-scale spike stem extracts early features, axial spike attention captures long-range dependencies, a dense spiking bottleneck enhances feature reuse, and a spike-to-continuous decoder reconstructs continuous intensity images from spike-domain representations. Experiments on gray-scale and color spike reconstruction show that MADSNet outperforms SSIR by 4.3 dB PSNR and Spk2ImgNet by 1.94 dB on SREDS. Compared with Spk2ImgNet, it achieves about 15$\times$ lower latency and uses only about 1/40 of the estimated energy, demonstrating that carefully designed SNN architectures can improve reconstruction quality while preserving computational efficiency.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Sirui Li, Rui Zhao, Siqi Cai, Haizhou Li, Tiejun Huang, Yajing Zheng. 2026-11-08. MADSNet: A Multi-Scale Axial-Attentive Dense Spiking Network for Spike Camera Image Reconstruction. https://searcharxiv.com/abs/2611.12980
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.