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 751–760 of 3874 papers

TitleStatusHype
Fast Samplers for Inverse Problems in Iterative Refinement ModelsCode0
PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-ResolutionCode1
Spectral-Refiner: Accurate Fine-Tuning of Spatiotemporal Fourier Neural Operator for Turbulent FlowsCode2
Does Diffusion Beat GAN in Image Super Resolution?Code1
Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models—0
Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models—0
BOLD: Boolean Logic Deep Learning—0
Stochastic super-resolution for Gaussian microtextures—0
Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem Solving—0
Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution—0
Show:102550
← PrevPage 76 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified