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 651–660 of 3874 papers

TitleStatusHype
DARTS: Double Attention Reference-based Transformer for Super-resolutionCode1
Diffusion Model Based Posterior Sampling for Noisy Linear Inverse ProblemsCode1
A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuningCode1
Conditional Simulation Using Diffusion Schrödinger BridgesCode1
Conditional Variational Diffusion ModelsCode1
Hierarchical Residual Attention Network for Single Image Super-ResolutionCode1
DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-ResolutionCode1
DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-ResolutionCode1
Conffusion: Confidence Intervals for Diffusion ModelsCode1
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution NetworksCode1
Show:102550
← PrevPage 66 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified