Research map / Video / Video segmentation and tracking
Store and Fetch Immediately: Everything Is All You Need for Space-Time Video Super-resolution
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 immediate store-and-fetch with bidirectional recurrent modules | ST-VSR · Vid4 | PSNR(Y): 26.43 vs 26.43 | No clear effect |
| Use immediate store-and-fetch with bidirectional recurrent modules | ST-VSR · Vimeo90K-Fast | PSNR(Y): 37.04 -> 37.12 | Helped |
| Use immediate store-and-fetch with bidirectional recurrent modules | ST-VSR · Vimeo90K-Medium | PSNR(Y): 35.60 -> 35.63 | Helped |
| Use immediate store-and-fetch with bidirectional recurrent modules | ST-VSR · Vimeo90K-Slow | PSNR(Y): 33.51 -> 33.49 | Hurt |
| Use the proposed method for S-VSR | Vimeo90K (Seven) · Vimeo90K (Seven) | PSNR(Y): 37.61 -> 37.22 | Hurt |
| Use the proposed method for T-VSR | Vimeo90K (Triplets) · Vimeo90K (Triplets) | PSNR: 35.07 -> 35.23 | Helped |
| Add adjacent fetch aggregation (ablation) | ST-VSR model (a) · Vimeo90K-Fast | PSNR: 36.20 -> 36.50 | Helped |
| Add distant fetch aggregation (ablation) | ST-VSR model (a) · Vimeo90K-Fast | PSNR: 36.20 -> 36.34 | Helped |
| Add adjacent and distant fetch blocks together (ablation) | ST-VSR · Vimeo90K-Fast | PSNR: 36.20 -> 36.64 | Helped |
| Add dynamic selection to guide spatial-feature fusion (ablation) | ST-VSR model (d) · Vimeo90K-Fast | PSNR: 36.64 -> 36.86 | Helped |
| Add a forward store-and-fetch container (ablation) | ST-VSR without bidirectional containers · Vimeo90K-Fast | PSNR: 36.47 -> 36.56 | Helped |
| Add a backward store-and-fetch container (ablation) | ST-VSR without bidirectional containers · Vimeo90K-Fast | PSNR: 36.47 -> 36.69 | Helped |
Closest papers by meaning
- Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning (CVPR 2022 · similarity 0.93)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.93)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.88)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.88)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.87)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.87)
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.