AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

SpikingIR: A Novel Converted Spiking Neural Network for Efficient Image Restoration

Yang Ouyang, Zihan Cheng, Xiaotong Luo, Guoqi Li, Yanyun Qu

AAAI 2026 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add surrogate-gradient fine-tuning to converted SNN (ablation)SpikingIR on AOD-Net · TestSet A dehazing (T=10)PSNR: 17.73 -> 18.26Improved
add CPM convolution layer (ablation)SpikingIR on AOD-Net · TestSet A dehazing (T=10)PSNR: 18.26 -> 19.27Improved
add RMPIS residual membrane potential shortcut (ablation)SpikingIR on AOD-Net · TestSet A dehazing (T=10)PSNR: 19.27 -> 19.59Improved
add MPRN neurons in intermediate layers (ablation)SpikingIR on AOD-Net · TestSet A dehazing (T=10)PSNR: 19.59 -> 19.90Improved
use CPM instead of directly outputting floating-point features (ablation)SpikingIR on AOD-Net · TestSet A dehazing (T=10)PSNR: 19.23 -> 19.59Improved
SpikingIR vs prior ANN-to-SNN conversion (Lan et al.) with fewer timestepsVDSR x4 super-resolution · Set5 x4PSNR: 28.722 -> 31.264Improved
convert dehazing ANN with SpikingIRAOD-Net · SOTS-outdoorPSNR: 20.12 -> 21.47Improved
convert denoising ANN with SpikingIRDnCNN · Set12 sigma=15PSNR: 32.859 -> 32.758Hurt
convert VDSR with SpikingIRVDSR · Set5 x2PSNR: 37.653 -> 37.459Hurt
use SpikingIR instead of ANN for energyAOD-Net · TestSet A dehazingenergy (mJ): 2.289 -> 0.931 (T=5)Improved
increase timesteps from 10 to 15SpikingIR on DnCNN · Set12 sigma=25PSNR: 30.160 -> 30.285Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy