SOTAVerified

Super-Resolution

Super-Resolution is a task in computer vision that involves increasing the resolution of an image or video by generating missing high-frequency details from low-resolution input. The goal is to produce an output image with a higher resolution than the input image, while preserving the original content and structure.

( Credit: MemNet )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 531–540 of 3874 papers

TitleStatusHype
U2Net: A General Framework with Spatial-Spectral-Integrated Double U-Net for Image FusionCode1
Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-ResolutionCode1
CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-ResolutionCode1
Learning Continuous Depth Representation via Geometric Spatial AggregatorCode1
RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal ShiftsCode1
Super-resolution Probabilistic Rain Prediction from Satellite Data Using 3D U-Nets and EarthFormersCode1
Learning Detail-Structure Alternative Optimization for Blind Super-ResolutionCode1
Bridging Component Learning with Degradation Modelling for Blind Image Super-ResolutionCode1
Global Learnable Attention for Single Image Super-ResolutionCode1
Knowledge Distillation based Degradation Estimation for Blind Super-ResolutionCode1
Show:102550
← PrevPage 54 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified