Video Super-Resolution
Video Super-Resolution is a computer vision task that aims to increase the resolution of a video sequence, typically from lower to higher resolutions. The goal is to generate high-resolution video frames from low-resolution input, improving the overall quality of the video.
( Image credit: Detail-revealing Deep Video Super-Resolution )
Papers
Showing 21–30 of 281 papers
All datasetsMSU Super-Resolution for Video CompressionMSU Video Upscalers: Quality EnhancementMSU Video Super Resolution Benchmark: Detail RestorationVid4 - 4x upscalingVid4 - 4x upscaling - BD degradationREDS4- 4x upscalingUDM10 - 4x upscalingUltra Video Group HD - 4x upscalingFalling ObjectsTbDTbD-3DVimeo90K
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | bicubic + uavs3e | BSQ-rate over ERQA | 21.97 | — | Unverified |
| 2 | bicubic + aomenc | BSQ-rate over ERQA | 21.97 | — | Unverified |
| 3 | RealSR + vvenc | BSQ-rate over ERQA | 21.97 | — | Unverified |
| 4 | bicubic + vvenc | BSQ-rate over ERQA | 21.97 | — | Unverified |
| 5 | TMNet + aomenc | BSQ-rate over ERQA | 21.8 | — | Unverified |
| 6 | TMNet + vvenc | BSQ-rate over ERQA | 21.3 | — | Unverified |
| 7 | RSDN + aomenc | BSQ-rate over ERQA | 20.62 | — | Unverified |
| 8 | RSDN + uavs3e | BSQ-rate over ERQA | 18.33 | — | Unverified |
| 9 | EGVSR + aomenc | BSQ-rate over ERQA | 16.73 | — | Unverified |
| 10 | bicubic + x265 | BSQ-rate over ERQA | 16.01 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | VRT | Subjective score | 7.63 | — | Unverified |
| 2 | BasicVSR | Subjective score | 7.19 | — | Unverified |
| 3 | RBPN | Subjective score | 7.07 | — | Unverified |
| 4 | DBVSR | Subjective score | 6.95 | — | Unverified |
| 5 | iSeeBetter | Subjective score | 6.81 | — | Unverified |
| 6 | LGFN | Subjective score | 6.51 | — | Unverified |
| 7 | DynaVSR-R | Subjective score | 6.14 | — | Unverified |
| 8 | TMNet | Subjective score | 6 | — | Unverified |
| 9 | COMISR | Subjective score | 5.64 | — | Unverified |
| 10 | RSDN | Subjective score | 5.57 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | VideoGigaGAN | PSNR | 27.04 | — | Unverified |
| 2 | TecoGAN⊖ | PSNR | 25.89 | — | Unverified |
| 3 | TecoGAN | PSNR | 25.57 | — | Unverified |
| 4 | EvTexture+ | SSIM | 0.9 | — | Unverified |
| 5 | EvTexture | SSIM | 0.89 | — | Unverified |
| 6 | IART | SSIM | 0.85 | — | Unverified |
| 7 | MIA-VSR | SSIM | 0.85 | — | Unverified |
| 8 | CFD-PSRT | SSIM | 0.85 | — | Unverified |
| 9 | PSRT-recurrent | SSIM | 0.85 | — | Unverified |
| 10 | RVRT | SSIM | 0.85 | — | Unverified |