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 1381–1390 of 3874 papers

TitleStatusHype
Debiased Subjective Assessment of Real-World Image Enhancement—0
Super-resolution of Time-series Labels for Bootstrapped Event Detection—0
DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration—0
AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution—0
Attention-Guided Multi-scale Interaction Network for Face Super-Resolution—0
A Hybrid Registration and Fusion Method for Hyperspectral Super-resolution—0
Generic Perceptual Loss for Modeling Structured Output Dependencies—0
DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior—0
DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution—0
DCIL: Deep Contextual Internal Learning for Image Restoration and Image Retargeting—0
Show:102550
← PrevPage 139 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified