Research map / Video / Video segmentation and tracking
Towards Interpretable Video Super-Resolution via Alternating Optimization
Jiezhang Cao, Jingyun Liang, Kai Zhang, Wenguan Wang, Qin Wang, Yulun Zhang, Hao Tang, Luc Van Gool
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 the Fourier data transform (FDT) layer to the recurrent enhancement network (ablation) | DAVSR · REDS4 | PSNR: 27.25 -> 29.12 | Improved |
| add the recurrent video enhancement (RVE) layer to the FDT layer (ablation) | DAVSR · REDS4 | PSNR: 23.05 -> 29.12 | Improved |
| replace two-stage SuperSloMo+BasicVSR++* pipeline with the one-stage DAVSR | STVSR on REDS4 · REDS4 (average) | PSNR: 26.93 -> 29.12 | Improved |
| replace two-stage SuperSloMo+BasicVSR++* pipeline with the one-stage DAVSR | STVSR on Vid4 · Vid4 (average) | PSNR: 20.22 -> 23.85 | Improved |
| use one-stage DAVSR instead of two-stage pipeline on small-motion clip | STVSR on REDS4 · REDS4 Clip_000 | PSNR: 28.00 -> 27.23 | Hurt |
| use one-stage DAVSR instead of two-stage pipeline on large-motion clip | STVSR on REDS4 · REDS4 Clip_020 | PSNR: 23.70 -> 28.06 | Improved |
| use two-stage instead of three-stage frame-interpolation/deblur/SR pipeline | DAIN+BasicVSR++ · REDS4 (average) | PSNR: 25.98 -> 26.53 | Improved |
| increase the number of alternating iterations | DAVSR · REDS4 | visual quality | Improved |
Closest papers by meaning
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.91)
- Turning Frequency to Resolution: Video Super-Resolution via Event Cameras (CVPR 2021 · similarity 0.90)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.90)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.90)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.89)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.89)
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.
