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 151–160 of 3874 papers

TitleStatusHype
Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion ModelsCode2
Implicit Diffusion Models for Continuous Super-ResolutionCode2
Learning Generative Structure Prior for Blind Text Image Super-resolutionCode2
SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-ResolutionCode2
StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned FacesCode2
Spatially-Adaptive Feature Modulation for Efficient Image Super-ResolutionCode2
I^2SB: Image-to-Image Schrödinger BridgeCode2
Image Restoration with Mean-Reverting Stochastic Differential EquationsCode2
Simple diffusion: End-to-end diffusion for high resolution imagesCode2
Reference-based Image and Video Super-Resolution via C2-MatchingCode2
Show:102550
← PrevPage 16 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified