Research map / Video / Video segmentation and tracking
Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset
Huanjing Yue, Zhiming Zhang, Jingyu Yang
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 |
|---|---|---|---|
| use co-alignment instead of separate alignment (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR/SSIM: 33.80 -> 33.91 PSNR; 0.9178 -> 0.9182 SSIM | Improved |
| add alignment module (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR: 33.72 -> 33.91 | Improved |
| add interaction module between branches (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR: 33.76 -> 33.91 | Improved |
| use selective kernel fusion instead of concatenation (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR: 33.85 -> 33.91 | Improved |
| add color correction (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR: 30.65 -> 33.91 | Improved |
| use channel-based instead of matrix-based color correction (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR: 33.81 -> 33.91 | Improved |
| use two branches (Bayer and sub-frame) instead of Bayer branch only (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR: 33.73 -> 33.91 | Improved |
| use two branches instead of sub-frame branch only (ablation) | Real-RawVSR · Real-RawVSR 4x | PSNR: 33.70 -> 33.91 | Improved |
| use raw Bayer input instead of sRGB input | EDVR-style VSR · Real-RawVSR 2x | PSNR/SSIM: 36.93 -> 36.74 PSNR; 0.9674 -> 0.9670 SSIM | Mixed |
| co-alignment instead of separate alignment (compute) (ablation) | Real-RawVSR · Real-RawVSR 4x | FLOPs: saves about 100G FLOPs | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- BasicVSR — BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (CVPR 2021) · better on 3 of 3 shared results
- TDAN — TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution (CVPR 2020) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning Scheme (ICCV 2021 · similarity 0.91)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.89)
- Investigating Tradeoffs in Real-World Video Super-Resolution (CVPR 2022 · similarity 0.88)
- Exploiting Raw Images for Real-Scene Super-Resolution (TPAMI 2020 · similarity 0.88)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · similarity 0.86)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.86)
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.
