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 731–740 of 3874 papers

TitleStatusHype
Journey Towards Tiny Perceptual Super-ResolutionCode1
Discovering Distinctive "Semantics" in Super-Resolution NetworksCode1
CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-ResolutionCode1
KeDuSR: Real-World Dual-Lens Super-Resolution via Kernel-Free MatchingCode1
CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed TomographyCode1
Action Matching: Learning Stochastic Dynamics from SamplesCode1
Diffusion Prior Interpolation for Flexibility Real-World Face Super-ResolutionCode1
Label-Efficient Semantic Segmentation with Diffusion ModelsCode1
A new public Alsat-2B dataset for single-image super-resolutionCode1
CADyQ: Content-Aware Dynamic Quantization for Image Super-ResolutionCode1
Show:102550
← PrevPage 74 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified