Research map / Video / Video segmentation and tracking
ClearSight: Human Vision-Inspired Solutions for Event-Based Motion Deblurring
Xiaopeng Lin, Yulong Huang, Hongwei Ren, Zunchang Liu, Hongxiang Huang, Yue Zhou, Haotian Fu, Bojun Cheng
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 |
|---|---|---|---|
| add event data (ablation) | image-only deblurring network · GoPro | PSNR: 31.64 -> 36.29 | Improved |
| add Neuron Configurator Module (ablation) | event+image network with add fusion · GoPro | PSNR: 36.29 -> 36.51 | Improved |
| add region of blurry mask (ablation) | NCM + add fusion · GoPro | PSNR: 36.51 -> 36.84 | Improved |
| add region of blurry mask (ablation) | NCM + cross attention · GoPro | PSNR: 36.60 -> 37.04 | Improved |
| replace add with cross attention fusion (ablation) | NCM, no mask · GoPro | PSNR: 36.51 -> 36.60 | Improved |
| replace add with cross attention fusion (ablation) | NCM + mask · GoPro | PSNR: 36.84 -> 37.04 | Improved |
| add NCM (ablation) | event+image network · GoPro | SSIM: 0.972 -> 0.973 | Improved |
| add mask and cross attention (ablation) | NCM network · GoPro | SSIM: 0.973 -> 0.977 | Improved |
| train on GoPro only, test on REBlur without fine-tuning (vs EFNet) (ablation) | BDHNet · REBlur (w/o fine-tune) | PSNR: 27.43 -> 36.01 | Improved |
| initialize membrane potential and configure thresholds at all timesteps vs first timestep only (ablation) | SNN branch · GoPro | training convergence | Improved |
Closest papers by meaning
- DeblurSR: Event-Based Motion Deblurring under the Spiking Representation (AAAI 2024 · similarity 0.89)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.89)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.87)
- Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment (CVPR 2024 · similarity 0.87)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.86)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.86)
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.
