Research map / Video / Video segmentation and tracking
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time 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 |
|---|---|---|---|
| Use one-stage joint feature interpolation and super-resolution instead of DAIN+EDVR | Zooming Slow-Mo · Vid4 | PSNR: 26.12 -> 26.31 | Helped |
| Use one-stage joint feature interpolation and super-resolution instead of DAIN+EDVR | Zooming Slow-Mo · Vimeo-Fast | PSNR: 35.81 -> 36.81 | Helped |
| Use one-stage joint feature interpolation and super-resolution instead of DAIN+EDVR | Zooming Slow-Mo · Vimeo-Medium | PSNR: 34.66 -> 35.41 | Helped |
| Use one-stage joint feature interpolation and super-resolution instead of DAIN+EDVR | Zooming Slow-Mo · Vimeo-Slow | PSNR: 33.11 -> 33.36 | Helped |
| Add deformable feature interpolation (ablation) | Zooming Slow-Mo · Vid4 (slow motion) | PSNR: 25.18 -> 25.34; +0.16dB | Helped |
| Add deformable feature interpolation (ablation) | Zooming Slow-Mo · Vimeo-Fast (fast motion) | PSNR: 34.93 -> 35.66; 0.73dB | Helped |
| Add vanilla ConvLSTM to DFI (ablation) | Zooming Slow-Mo · Vid4 (slow motion) | PSNR: 25.34 -> 25.68 | Helped |
| Add vanilla ConvLSTM to DFI (ablation) | Zooming Slow-Mo · Vimeo-Fast (fast motion) | PSNR: 35.66 -> 35.39 | Hurt |
| Replace vanilla ConvLSTM with deformable ConvLSTM (ablation) | Zooming Slow-Mo · Vimeo-Fast (fast motion) | PSNR: 35.39 -> 36.56 | Helped |
| Add bidirectional processing to DConvLSTM (ablation) | Zooming Slow-Mo · Vid4 (slow motion) | PSNR: 26.18 -> 26.31 | Helped |
| Add bidirectional processing to DConvLSTM (ablation) | Zooming Slow-Mo · Vimeo-Fast (fast motion) | PSNR: 36.56 -> 36.81 | Helped |
Closest papers by meaning
- Frame and Feature-Context Video Super-Resolution (AAAI 2019 · similarity 0.91)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.90)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- Arbitrary-Scale Video Super-resolution Guided by Dynamic Context (AAAI 2024 · similarity 0.87)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 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.