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

Showing 201250 of 281 papers

TitleStatusHype
Deep Learning Techniques for Super-Resolution in Video Games0
EVRNet: Efficient Video Restoration on Edge Devices0
BasicVSR: The Search for Essential Components in Video Super-Resolution and BeyondCode3
DeFMO: Deblurring and Shape Recovery of Fast Moving ObjectsCode1
Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition0
Recursive Deep Prior Video: a Super Resolution algorithm for Time-Lapse Microscopy of organ-on-chip experiments0
DynaVSR: Dynamic Adaptive Blind Video Super-ResolutionCode1
Real-time Surgical Environment Enhancement for Robot-Assisted Minimally Invasive Surgery Based on Super-Resolution0
Deformable Kernel Convolutional Network for Video Extreme Super-Resolution0
Local-Global Fusion Network for Video Super-ResolutionCode1
NEMO: enabling neural-enhanced video streaming on commodity mobile devicesCode1
Understanding Deformable Alignment in Video Super-Resolution0
AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results0
A Single Frame and Multi-Frame Joint Network for 360-degree Panorama Video Super-ResolutionCode1
Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model InferenceCode1
Revisiting Temporal Modeling for Video Super-resolutionCode1
Video Super-Resolution with Recurrent Structure-Detail NetworkCode1
Blind Face Restoration via Deep Multi-scale Component DictionariesCode1
Neural supersampling for real-time renderingCode1
Video Super Resolution Based on Deep Learning: A Comprehensive Survey0
MuCAN: Multi-Correspondence Aggregation Network for Video Super-ResolutionCode1
Video Super-resolution with Temporal Group AttentionCode1
Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural NetworksCode1
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection NetworksCode1
Real-World Super-Resolution via Kernel Estimation and Noise InjectionCode2
iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networksCode1
TDAN: Temporally-Deformable Alignment Network for Video Super-ResolutionCode1
Efficient and Phase-aware Video Super-resolution for Cardiac MRI0
Deformable 3D Convolution for Video Super-ResolutionCode1
Deep Space-Time Video Upsampling NetworksCode1
Space-Time-Aware Multi-Resolution Video EnhancementCode1
Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal LearningCode1
Is There Tradeoff between Spatial and Temporal in Video Super-Resolution?0
Deep Blind Video Super-resolutionCode1
Deep Slow Motion Video Reconstruction with Hybrid Imaging SystemCode1
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-ResolutionCode1
Video Face Super-Resolution with Motion-Adaptive Feedback Cell0
Deep Video Super-Resolution using HR Optical Flow EstimationCode1
End-To-End Trainable Video Super-Resolution Based on a New Mechanism for Implicit Motion Estimation and Compensation0
Self-supervised Fine-tuning for Correcting Super-Resolution Convolutional Neural Networks0
FISR: Deep Joint Frame Interpolation and Super-Resolution with a Multi-scale Temporal LossCode0
Sub-frame Appearance and 6D Pose Estimation of Fast Moving ObjectsCode0
Self-Enhanced Convolutional Network for Facial Video Hallucination0
Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal CorrelationsCode0
Frame and Feature-Context Video Super-Resolution0
Deformable Non-local Network for Video Super-ResolutionCode0
Robust Online Video Super-Resolution Using an Efficient Alternating Projections Scheme0
A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models0
Intra-frame Object Tracking by DeblattingCode0
EDVR: Video Restoration with Enhanced Deformable Convolutional NetworksCode1
Show:102550
← PrevPage 5 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1bicubic + uavs3eBSQ-rate over ERQA21.97Unverified
2bicubic + aomencBSQ-rate over ERQA21.97Unverified
3RealSR + vvencBSQ-rate over ERQA21.97Unverified
4bicubic + vvencBSQ-rate over ERQA21.97Unverified
5TMNet + aomencBSQ-rate over ERQA21.8Unverified
6TMNet + vvencBSQ-rate over ERQA21.3Unverified
7RSDN + aomencBSQ-rate over ERQA20.62Unverified
8RSDN + uavs3eBSQ-rate over ERQA18.33Unverified
9EGVSR + aomencBSQ-rate over ERQA16.73Unverified
10bicubic + x265BSQ-rate over ERQA16.01Unverified
#ModelMetricClaimedVerifiedStatus
1iSeeBetterSSIM0.94Unverified
2LGFNSSIM0.94Unverified
3SOF-VSRSSIM0.94Unverified
4DBVSRSSIM0.94Unverified
5FRVSRSSIM0.94Unverified
6ESRGANSSIM0.94Unverified
7DRRNSSIM0.93Unverified
8TecoGANSSIM0.93Unverified
9SPMCSSIM0.93Unverified
10VESPCNSSIM0.93Unverified
#ModelMetricClaimedVerifiedStatus
1VRTSubjective score7.63Unverified
2BasicVSRSubjective score7.19Unverified
3RBPNSubjective score7.07Unverified
4DBVSRSubjective score6.95Unverified
5iSeeBetterSubjective score6.81Unverified
6LGFNSubjective score6.51Unverified
7DynaVSR-RSubjective score6.14Unverified
8TMNetSubjective score6Unverified
9COMISRSubjective score5.64Unverified
10RSDNSubjective score5.57Unverified
#ModelMetricClaimedVerifiedStatus
1VideoGigaGANPSNR27.04Unverified
2TecoGAN⊖PSNR25.89Unverified
3TecoGANPSNR25.57Unverified
4EvTexture+SSIM0.9Unverified
5EvTextureSSIM0.89Unverified
6IARTSSIM0.85Unverified
7MIA-VSRSSIM0.85Unverified
8CFD-PSRTSSIM0.85Unverified
9PSRT-recurrentSSIM0.85Unverified
10RVRTSSIM0.85Unverified
#ModelMetricClaimedVerifiedStatus
1RVRTPSNR29.54Unverified
2VRTPSNR29.42Unverified
3BasicVSR++PSNR29.04Unverified
4FTVSRPSNR28.7Unverified
5GOVSRPSNR28.41Unverified
6TTVSRPSNR28.4Unverified
7IconVSRPSNR28.04Unverified
8BasicVSRPSNR27.96Unverified