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 971–980 of 3874 papers

TitleStatusHype
Deep Space-Time Video Upsampling NetworksCode1
Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency RegularizationCode1
Robust Single-Image Super-Resolution via CNNs and TV-TV MinimizationCode1
Unsupervised Real-world Image Super Resolution via Domain-distance Aware TrainingCode1
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New StrategyCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Space-Time-Aware Multi-Resolution Video EnhancementCode1
Structure-Preserving Super Resolution with Gradient GuidanceCode1
Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark EstimationCode1
High-Order Residual Network for Light Field Super-ResolutionCode1
Show:102550
← PrevPage 98 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified