cs.LGNov 8, 2026

MADSNet: A Multi-Scale Axial-Attentive Dense Spiking Network for Spike Camera Image Reconstruction

Authors: Sirui Li, Rui Zhao, Siqi Cai, Haizhou Li, Tiejun Huang, Yajing Zheng

Organizations: School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · School of Computer Science, Peking University, Beijing, China · College of Computing and Data Science, Nanyang Technological University, Singapore · School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China · 

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.

Figures & tables

Explore similar work

CardsList
  1. SpikeRestormer: Towards Energy-Efficient All-in-One Image Restoration via Unified Event Reasoning

    Aug 3, 2026Shengkai Hu, Jie Shao, Jiaqi Ma +5Efficient Neural Network InferenceAll-in-One Image Restoration

  2. Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells

    Oct 12, 2026Ning Zhang, Arto NurmikkoNeural DecodingImage Reconstruction

  3. Spiking Pyramid Wavelet Transformation for High-efficient and Low-energy Image Restoration

    Jun 17, 2026Chen Zhao, Xiantao Hu, Song Wu +5Efficient Neural Network InferenceWavelet Methods