Research map / Video / Video segmentation and tracking
Collaborative Feedback Discriminative Propagation for Video Super-Resolution
Hui Li, Xiang Chen, Jiangxin Dong, Jinhui Tang, Jinshan Pan
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 DAC and CFP propagation to BasicVSR | BasicVSR · REDS4 (BI x4) | PSNR: 31.42 -> 31.79 | Improved |
| add CFD propagation to BasicVSR | BasicVSR · Vimeo-T (BD x4) | PSNR: 0.42dB | Improved |
| add CFD propagation to BasicVSR++ | BasicVSR++ · REDS4 (BI x4) | PSNR: 32.39 -> 32.51 | Improved |
| add CFD propagation to PSRT | PSRT · REDS4 (BI x4) | PSNR: 32.72 -> 32.83 | Improved |
| add discriminative alignment correction (DAC) (ablation) | baseline VSR · REDS4 ablation (300K iters) | PSNR: 31.36 -> 31.57 | Improved |
| add DAC on top of CFP (ablation) | baseline VSR with CFP · REDS4 ablation (300K iters) | PSNR: 31.50 -> 31.79 | Improved |
| replace concatenation with DAC (ablation) | baseline VSR · REDS4 ablation (300K iters) | PSNR: 31.48 -> 31.57 | Improved |
| add collaborative feedback propagation (CFP) (ablation) | baseline VSR with DAC · REDS4 ablation (300K iters) | PSNR: 31.57 -> 31.79 | Improved |
| replace Resblocks with GCFBs in CFP (ablation) | CFP · GCFB ablation (CFP variants) | PSNR: 31.69 -> 31.79 | Improved |
| replace GDFNs with GCFBs in CFP (ablation) | CFP · GCFB ablation (CFP variants) | PSNR: 31.63 -> 31.79 | Improved |
| add temporal interaction to GDFNs (ablation) | CFP with GDFN · GCFB ablation (CFP variants) | PSNR: 31.63 -> 31.70 | Improved |
| use CFD-BasicVSR++ instead of VRT | VRT · REDS4 (BI x4) | PSNR: 0.32dB | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BasicVSR — BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (CVPR 2021) · better on 8 of 9 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
- Rethinking Alignment in Video Super-Resolution Transformers (NeurIPS 2022 · similarity 0.89)
- TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution (CVPR 2020 · similarity 0.88)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.87)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · similarity 0.87)
- One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution (NeurIPS 2025 · 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.
