Research map / Video / Video segmentation and tracking
Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning Scheme
Xi Yang, Wangmeng Xiang, Hui Zeng, Lei Zhang
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 |
|---|---|---|---|
| train on RealVSR instead of synthetic Vimeo-90k | EDVR · RealVSR test set | PSNR (Y): 24.58 -> 25.60 | Improved |
| train on RealVSR instead of synthetic Vimeo-90k | RCAN · RealVSR test set | PSNR (Y): 24.66 -> 25.50 | Improved |
| train on Vimeo-90k instead of nothing (bicubic) | FSTRN · RealVSR test set | PSNR (Y): 24.67 -> 24.63 | Hurt |
| train on RealVSR instead of Vimeo-90k | EDVR · RealVSR test set | SSIM (Y): 0.7838 -> 0.8102 | Improved |
| train on RealVSR instead of Vimeo-90k | EDVR · RealVSR test set | NIQE: 4.6377 -> 3.9082 | Improved |
| train on RealVSR instead of Vimeo-90k | EDVR · RealVSR test set | T-diff: 4.4229 -> 3.6860 | Improved |
| add Laplacian pyramid losses Ls and Ld on Y channel (ablation) | EDVR · RealVSR test set | PSNR (Y): 25.60 -> 25.83 | Improved |
| add Laplacian pyramid losses Ls and Ld on Y channel (ablation) | TOF · RealVSR test set | PSNR (Y): 25.59 -> 25.65 | Improved |
| add gradient weighted chroma loss Lc (ablation) | EDVR · RealVSR test set | PSNR (Y): 25.83 -> 25.83 | No clear effect |
| replace RaGAN discriminator with multi-scale edge-based GAN (Lv2) (ablation) | EDVR · RealVSR test set | LPIPS: 0.2598 -> 0.2459 | Improved |
| replace RaGAN discriminator with multi-scale edge-based GAN (Lv2) (ablation) | EDVR · RealVSR test set | DISTS: 0.0852 -> 0.0766 | Improved |
| replace RaGAN discriminator with multi-scale edge-based GAN (Lv2) (ablation) | TOF · RealVSR test set | LPIPS: 0.2625 -> 0.2622 | Improved |
Closest papers by meaning
- Investigating Tradeoffs in Real-World Video Super-Resolution (CVPR 2022 · similarity 0.93)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.91)
- NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-world Video Super-Resolution (AAAI 2024 · similarity 0.90)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · similarity 0.89)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.88)
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.
