Research map / Video / Video segmentation and tracking
BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
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 bidirectional instead of unidirectional propagation (ablation) | BasicVSR · video super-resolution sequences | PSNR: 0.5 dB | Helped |
| Remove spatial alignment (ablation) | BasicVSR · video super-resolution | PSNR: 1.19 dB | Hurt |
| Use image warping instead of feature warping (ablation) | BasicVSR variant · video super-resolution | PSNR: 0.17 dB | Hurt |
| Add coupled propagation (ablation) | BasicVSR · REDS4 | PSNR: 31.42 -> 31.60 | Helped |
| Add coupled propagation (ablation) | BasicVSR · REDSval4 | PSNR: 30.17 -> 30.38 | Helped |
| Add information-refill to coupled propagation (ablation) | IconVSR without refill · REDS4 | PSNR: 31.60 -> 31.67 | Helped |
| Add information-refill to coupled propagation (ablation) | IconVSR without refill · REDSval4 | PSNR: 30.38 -> 30.45 | Helped |
| Use more keyframes for information-refill (ablation) | IconVSR · REDSval4 | PSNR | Helped |
| Use no keyframes, retaining coupled propagation (ablation) | IconVSR · REDSval4 | PSNR: 30.38 dB; 0.21 dB higher | Helped |
| Aggregate long-term information with global rather than segmented propagation (ablation) | BasicVSR · video super-resolution sequences | PSNR | Helped |
| Use IconVSR instead of BasicVSR | BasicVSR · REDS4 | PSNR: 31.42 -> 31.67 | Helped |
| Use IconVSR instead of BasicVSR | BasicVSR · Vimeo-90K-T BI | PSNR: 37.18 -> 37.47 | Helped |
Closest papers by meaning
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.89)
- NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-world Video Super-Resolution (AAAI 2024 · similarity 0.89)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · similarity 0.89)
- Arbitrary-Scale Video Super-resolution Guided by Dynamic Context (AAAI 2024 · similarity 0.88)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.88)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · 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.