Research map / 3D vision / Depth and stereo
Seeing Through Blur: Tackling Defocus in Spike-Based Imaging
Xiantao Ma, Siwei Dong, Lin Zhu, Lizhi Wang, Hua Huang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use DeSpike instead of best reconstruct-then-deblur pipeline | defocus spike reconstruction · Simulated DPDD spike data | PSNR: 17.77 -> 18.94 | Improved |
| use DeSpike instead of TFP-GKMNet | defocus spike reconstruction · Simulated DPDD spike data | SSIM: 0.58 -> 0.57 | Hurt |
| use DeSpike instead of best baseline on real data | defocus spike reconstruction · Real spike data | Contrast: 0.12 -> 0.15 | Improved |
| add multi-temporal-scale design (ablation) | DeSpike · Simulated DPDD spike data | PSNR: 18.28 -> 18.94 | Improved |
| add multi-scale iterative refinement (ablation) | DeSpike · Simulated DPDD spike data | PSNR: 18.20 -> 18.94 | Improved |
| add FPN compensation (NC) to IF neurons (ablation) | DeSpike · Simulated DPDD spike data | PSNR: 17.36 -> 18.94 | Improved |
| use Transformer fusion instead of QKV attention (ablation) | DeSpike · Simulated DPDD spike data | PSNR: 17.02 -> 18.94 | Improved |
| use physical PSF kernel priors instead of plain conv layers (ablation) | DeSpike · Simulated DPDD spike data | PSNR: 18.48 -> 18.94 | Improved |
| use shorter spike time windows (ablation) | DeSpike · Real spike data | qualitative quality | Hurt |
Closest papers by meaning
- SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams (NeurIPS 2024 · similarity 0.89)
- Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment (CVPR 2024 · similarity 0.88)
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.88)
- EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams (ICML 2025 · similarity 0.87)
- DeblurSR: Event-Based Motion Deblurring under the Spiking Representation (AAAI 2024 · similarity 0.87)
- Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model (CVPR 2025 · similarity 0.87)
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.
