SOTAVerified

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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 281 papers

TitleStatusHype
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion ModelsCode1
A Lightweight Recurrent Aggregation Network for Satellite Video Super-ResolutionCode1
VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic DataCode1
Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-ResolutionCode1
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion ModelsCode1
MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-ResolutionCode1
EgoVSR: Towards High-Quality Egocentric Video Super-ResolutionCode1
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion ModelsCode1
Local-Global Temporal Difference Learning for Satellite Video Super-ResolutionCode1
Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-ResolutionCode1
Show:102550
← PrevPage 5 of 29Next →
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

#ModelMetricClaimedVerifiedStatus
1bicubic + uavs3eBSQ-rate over ERQA21.97—Unverified
2bicubic + aomencBSQ-rate over ERQA21.97—Unverified
3RealSR + vvencBSQ-rate over ERQA21.97—Unverified
4bicubic + vvencBSQ-rate over ERQA21.97—Unverified
5TMNet + aomencBSQ-rate over ERQA21.8—Unverified
6TMNet + vvencBSQ-rate over ERQA21.3—Unverified
7RSDN + aomencBSQ-rate over ERQA20.62—Unverified
8RSDN + uavs3eBSQ-rate over ERQA18.33—Unverified
9EGVSR + aomencBSQ-rate over ERQA16.73—Unverified
10bicubic + x265BSQ-rate over ERQA16.01—Unverified
#ModelMetricClaimedVerifiedStatus
1iSeeBetterSSIM0.94—Unverified
2LGFNSSIM0.94—Unverified
3SOF-VSRSSIM0.94—Unverified
4DBVSRSSIM0.94—Unverified
5FRVSRSSIM0.94—Unverified
6ESRGANSSIM0.94—Unverified
7DRRNSSIM0.93—Unverified
8TecoGANSSIM0.93—Unverified
9SPMCSSIM0.93—Unverified
10VESPCNSSIM0.93—Unverified
#ModelMetricClaimedVerifiedStatus
1VRTSubjective score7.63—Unverified
2BasicVSRSubjective score7.19—Unverified
3RBPNSubjective score7.07—Unverified
4DBVSRSubjective score6.95—Unverified
5iSeeBetterSubjective score6.81—Unverified
6LGFNSubjective score6.51—Unverified
7DynaVSR-RSubjective score6.14—Unverified
8TMNetSubjective score6—Unverified
9COMISRSubjective score5.64—Unverified
10RSDNSubjective score5.57—Unverified
#ModelMetricClaimedVerifiedStatus
1VideoGigaGANPSNR27.04—Unverified
2TecoGAN⊖PSNR25.89—Unverified
3TecoGANPSNR25.57—Unverified
4EvTexture+SSIM0.9—Unverified
5EvTextureSSIM0.89—Unverified
6IARTSSIM0.85—Unverified
7MIA-VSRSSIM0.85—Unverified
8CFD-PSRTSSIM0.85—Unverified
9PSRT-recurrentSSIM0.85—Unverified
10RVRTSSIM0.85—Unverified
#ModelMetricClaimedVerifiedStatus
1RVRTPSNR29.54—Unverified
2VRTPSNR29.42—Unverified
3BasicVSR++PSNR29.04—Unverified
4FTVSRPSNR28.7—Unverified
5GOVSRPSNR28.41—Unverified
6TTVSRPSNR28.4—Unverified
7IconVSRPSNR28.04—Unverified
8BasicVSRPSNR27.96—Unverified