Research map / Video / Video segmentation and tracking
Space-Time Distillation for Video Super-Resolution
Check 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 |
|---|---|---|---|
| Add space-time distillation (SD and TD) from EDVR | FastDVDnet · Vid4 testset | PSNR (dB): 25.43 -> 26.14 | Helped |
| Add space-time distillation (SD and TD) from EDVR | FastDVDnet · Vimeo90K-Test | PSNR (dB): 34.48 -> 36.12 | Helped |
| Add space distillation only (ablation) | FastDVDnet · Vid4 testset | PSNR (dB): 25.43 -> 25.95 | Helped |
| Add time distillation only (ablation) | FastDVDnet · Vid4 testset | PSNR (dB): 25.43 -> 25.87 | Helped |
| Add both SD and TD rather than neither (ablation) | FastDVDnet · Vid4 testset | PSNR (dB): 25.43 -> 26.14 | Helped |
| Use the proposed STD scheme instead of MSE feature matching (ablation) | FastDVDnet · Vid4 testset | PSNR (dB): 25.86 -> 26.14 | Helped |
| Use the proposed STD scheme instead of KD-M²mean (ablation) | FastDVDnet · Vid4 testset | PSNR (dB): 25.92 -> 26.14 | Helped |
| Distill high-resolution features rather than low-resolution features (ablation) | FastDVDnet · Vid4 testset | PSNR (dB): 26.09 -> 26.14 | Helped |
| Use EDVR rather than RBPN as the teacher (ablation) | FastDVDnet with STD · Vid4 testset | PSNR (dB): 25.89 -> 26.14 | Helped |
| Add STD to FastDVDnet at 1/4 model size (ablation) | FastDVDnet · Vid4-Walk | PSNR (dB): 25.70 -> 27.06 | Helped |
| Add STD to FastDVDnet at 1/2 model size (ablation) | FastDVDnet · Vid4-Walk | PSNR (dB): 26.67 -> 27.35 | Helped |
| Add STD to original-size FastDVDnet (ablation) | FastDVDnet · Vid4-Walk | PSNR (dB): 28.45 -> 29.22 | Helped |
Closest papers by meaning
- Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning (CVPR 2022 · similarity 0.91)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.89)
- Building an End-to-End Spatial-Temporal Convolutional Network for Video Super-Resolution (AAAI 2017 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.87)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.87)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image 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.