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 91–100 of 3874 papers

TitleStatusHype
Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel FusionCode2
CoSeR: Bridging Image and Language for Cognitive Super-ResolutionCode2
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and ResultsCode2
Dual Aggregation Transformer for Image Super-ResolutionCode2
Deep Constrained Least Squares for Blind Image Super-ResolutionCode2
AERO: Audio Super Resolution in the Spectral DomainCode2
AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space modelsCode2
Efficient Long-Range Attention Network for Image Super-resolutionCode2
Auto-Encoded Supervision for Perceptual Image Super-ResolutionCode2
Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differencesCode2
Show:102550
← PrevPage 10 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified