Research map / Image generation / Image restoration
Perceptual Variousness Motion Deblurring With Light Global Context Refinement
Jichun Li, Weimin Tan, Bo Yan
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 LGCR module (Baseline2 vs full SimpleNet) (ablation) | SimpleNet · GoPro | PSNR (dB): 31.19 -> 31.52 | Improved |
| add LGCR module (Baseline2 vs full SimpleNet) (ablation) | SimpleNet · GoPro | SSIM: 0.9459 -> 0.9495 | Improved |
| add Non-Local module to Baseline2 (ablation) | SimpleNet Baseline2 · GoPro | PSNR (dB): 31.19 -> 31.39 | Improved |
| add T+T module to Baseline2 (ablation) | SimpleNet Baseline2 · GoPro | PSNR (dB): 31.19 -> 30.83 | Hurt |
| add T+T module to Baseline2 (ablation) | SimpleNet Baseline2 · GoPro | SSIM: 0.9459 -> 0.9158 | Hurt |
| use LGCR instead of Non-Local (ablation) | SimpleNet Baseline2 · GoPro | PSNR (dB): 31.39 -> 31.52 | Improved |
| use LGCR instead of Non-Local (ablation) | SimpleNet · Memory cost, 180x180x3 input | memory (M): 8018M -> 34M | Improved |
| insert LGCR into Tao et al. network (ablation) | Tao et al. [25] · GoPro | PSNR (dB): 30.26 -> 30.38 | Improved |
| apply PVB at each scale of Tao et al. network (ablation) | Tao et al. [25] · GoPro | PSNR (dB): 30.26 -> 30.41 | Improved |
| add all three modules PVB, LGCR, DR (vs Baseline3) (ablation) | SimpleNet · GoPro | PSNR (dB): 31.04 -> 31.52 | Improved |
| add all three modules (vs Baseline1) (ablation) | SimpleNet · GoPro | PSNR (dB): 31.24 -> 31.52 | Improved |
| use SimpleNet vs GAN-trained Kupyn et al. on no-reference quality | SimpleNet · RWBI (no reference) | Deblur-IQA: -7.7350 -> -7.9188 | Hurt |
Closest papers by meaning
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.88)
- Adaptive Window Pruning for Efficient Local Motion Deblurring (ICLR 2024 · similarity 0.87)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · similarity 0.87)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.87)
- Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring (CVPR 2024 · similarity 0.87)
- Exploiting Deblurring Networks for Radiance Fields (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.
