Research map / Video / Video segmentation and tracking
Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations
Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang, Jiayi Ma
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 one non-local residual block (r=1) as preprocessing (ablation) | VSR · training Vid validation | PSNR (dB): about 0.14 dB | Improved |
| add SPMC motion compensation as preprocessing (ablation) | VSR · training validation | PSNR (dB): about 0.04 dB | No clear effect |
| add STMC motion compensation as preprocessing (ablation) | VSR · training validation | PSNR (dB) | No clear effect |
| increase non-local down-scale from r=1 to r=2 (ablation) | VSR-NL · training validation | PSNR (dB) | No clear effect |
| share parameters across channels (CCPS) (ablation) | PFS · fusion comparison | PSNR (dB): 31.21 -> 31.17 | Hurt |
| share parameters across blocks (CBPS) (ablation) | DFS · fusion comparison | PSNR (dB): 30.98 -> 30.75 | Hurt |
| share parameters across blocks (CBPS) (ablation) | SFS · fusion comparison | PSNR (dB): 30.86 -> 30.73 | Hurt |
| share parameters across blocks (CBPS) (ablation) | 3DFS · fusion comparison | PSNR (dB): 31.18 -> 30.82 | Hurt |
| use progressive fusion PFS instead of 3D convolution fusion (ablation) | 3DFS · fusion comparison | PSNR (dB): 31.18 -> 31.21 | Improved |
| use direct fusion instead of slow fusion (ablation) | SFS · fusion comparison | PSNR (dB): 30.86 -> 30.98 | Improved |
| increase input frames from 3 to 5 to 7 (ablation) | PFS-PS · fusion comparison | PSNR (dB) | Improved |
| use PFNL instead of DUF 52L | DUF 52L · 10 sequences 1272x720 | PSNR (dB): about 0.96 dB | Improved |
Closest papers by meaning
- A Progressive Fusion Generative Adversarial Network for Realistic and Consistent Video Super-Resolution (TPAMI 2020 · similarity 0.93)
- Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (CVPR 2017 · similarity 0.92)
- Residual Invertible Spatio-Temporal Network for Video Super-Resolution (AAAI 2019 · similarity 0.88)
- Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning (CVPR 2022 · similarity 0.87)
- Fast Spatio-Temporal Residual Network for Video Super-Resolution (CVPR 2019 · similarity 0.87)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 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.
