Research map / Video / Video segmentation and tracking
Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring
Senyou Deng, Wenqi Ren, Yanyang Yan, Tao Wang, Fenglong Song, Xiaochun Cao
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 separable-patch acceleration architecture (SPAA) (ablation) | UHDVD · 720x1280 frames | time per image: 32.5 ms -> 12.5 ms | Improved |
| add separable-patch acceleration architecture (SPAA) (ablation) | UHDVD · 2160x3840 frames | time per image: 65.6 ms -> 27.9 ms | Improved |
| add separable-patch acceleration architecture (SPAA) (ablation) | UHDVD · 720x1280 frames | PSNR: 29.76 -> 29.74 | No clear effect |
| add separable-patch acceleration architecture (SPAA) (ablation) | UHDVD · 2160x3840 frames | PSNR: 27.62 -> 27.61 | No clear effect |
| add RCSA module (channel and spatial attention) (ablation) | UHDVD · GoPro | PSNR: 30.64 -> 31.33 | Improved |
| add RCSA module (channel and spatial attention) (ablation) | UHDVD · DVD | PSNR: 31.57 -> 32.19 | Improved |
| add RCSA module (channel and spatial attention) (ablation) | UHDVD · REDS | PSNR: 26.64 -> 27.53 | Improved |
| add RCSA module (channel and spatial attention) (ablation) | UHDVD · 4KRD | PSNR: 27.38 -> 27.88 | Improved |
| add RCSA module (channel and spatial attention) (ablation) | UHDVD · 4KRD | time per image: 22.6 -> 27.9 | Hurt |
Closest papers by meaning
- Real-World Video Deblurring: A Benchmark Dataset and an Efficient Recurrent Neural Network (IJCV 2022 · similarity 0.89)
- Deep Recurrent Neural Network with Multi-Scale Bi-directional Propagation for Video Deblurring (AAAI 2022 · similarity 0.88)
- Fast Ultra High-Definition Video Deblurring via Multi-scale Separable Network (IJCV 2023 · similarity 0.88)
- Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-Local Spatial-Temporal Similarity (TPAMI 2023 · similarity 0.88)
- Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring (CVPR 2019 · similarity 0.88)
- LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing (NeurIPS 2026 · 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.
