Research map / Video / Video segmentation and tracking
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time 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 continuous space-time representation rather than the strongest reported baseline | VideoINR · GoPro-Average | PSNR: 26.46 -> 29.41 | Helped |
| Use continuous space-time representation rather than the strongest reported baseline | VideoINR · Adobe-Average | PSNR: 26.23 -> 29.27 | Helped |
| Use VideoINR instead of VideoINR-fixed | VideoINR · GoPro-Center | PSNR: 30.73 -> 30.26 | Hurt |
| Use VideoINR instead of Zooming SlowMo | VideoINR · GoPro, time ×4, space ×16 | PSNR: 23.38 -> 23.45 | Helped |
| Add motion flow correspondence (ablation) | VideoINR · GoPro-Average | PSNR: 28.76 -> 29.41 | Helped |
| Add multi-scale feature aggregation (ablation) | VideoINR · GoPro-Average | PSNR: 29.28 -> 29.41 | Helped |
| Use separate spatial and temporal functions instead of one network for both (ablation) | VideoINR · GoPro-Average | PSNR: 29.20 -> 29.41 | Helped |
| Use the two-stage scale-training strategy rather than training continuous scales from scratch (ablation) | VideoINR · GoPro-Average, space ×2 | PSNR: 27.46 -> 29.61 | Helped |
| Fix the spatial training scale at ×4 instead of using the two-stage scale strategy (ablation) | VideoINR · GoPro-Average, space ×4 | PSNR: 29.41 -> 29.50 | Helped |
| Use the two-stage scale-training strategy rather than fixing training at ×4 (ablation) | VideoINR · GoPro-Average, space ×2 | PSNR: 28.25 -> 29.61 | Helped |
Closest papers by meaning
- Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution (CVPR 2023 · similarity 0.91)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.91)
- Bias for Action: Video Implicit Neural Representations with Bias Modulation (CVPR 2025 · similarity 0.90)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.90)
- Boosting Neural Representations for Videos with a Conditional Decoder (CVPR 2024 · similarity 0.88)
- Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions (CVPR 2024 · 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.