Research map / 3D vision / Depth and stereo
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 spatially variant RNN deconvolution instead of the strongest listed baseline | Dynamic scene deblurring · Dynamic scene deblurring dataset [21] | PSNR: 28.4898 -> 29.1872 | Helped |
| Use spatially variant RNN deconvolution instead of the strongest listed baseline | Dynamic scene deblurring · Dynamic scene deblurring dataset [21] | SSIM: 0.9165 -> 0.9306 | Helped |
| Use the proposed model instead of Nah et al. [21] | Deblurring a 720×1280 image · 720×1280 image | time(sec): 15 -> 1.4 | Helped |
| Use the proposed model instead of Nah et al. [21] | Deblurring a 720×1280 image · 720×1280 image | size(MB): 303.6 -> 37.1 | Helped |
| Add skip links (ablation) | Proposed deblurring network · Dynamic scene deblurring dataset [21] | PSNR: 25.7687 -> 29.1872 | Helped |
| Add convolution layers between consecutive RNNs (ablation) | Proposed deblurring network · Dynamic scene deblurring dataset [21] | PSNR: 27.8365 -> 29.1872 | Helped |
| Add spatially variant RNNs (ablation) | Proposed deblurring network · Dynamic scene deblurring dataset [21] | PSNR: 26.0413 -> 29.1872 | Helped |
| Use the full network rather than only the weight-generation network (ablation) | Proposed deblurring network · Dynamic scene deblurring dataset [21] | PSNR: 27.6835 -> 29.1872 | Helped |
Closest papers by meaning
- Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided Training (CVPR 2020 · similarity 0.93)
- Exploiting Deblurring Networks for Radiance Fields (CVPR 2025 · similarity 0.86)
- Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring (CVPR 2024 · similarity 0.86)
- Efficient Visual State Space Model for Image Deblurring (CVPR 2025 · similarity 0.86)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.85)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.85)
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.