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 281–290 of 3874 papers

TitleStatusHype
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory DistillationCode3
A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers—0
Low Resource Video Super-resolution using Memory and Residual Deformable Convolutions—0
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-ResolutionCode1
Exploring Linear Attention Alternative for Single Image Super-ResolutionCode0
Visual Autoregressive Modeling for Image Super-ResolutionCode2
Distillation-Driven Diffusion Model for Multi-Scale MRI Super-Resolution: Make 1.5T MRI Great AgainCode1
Rethinking the Upsampling Layer in Hyperspectral Image Super Resolution—0
HSRMamba: Contextual Spatial-Spectral State Space Model for Single Image Hyperspectral Super-ResolutionCode1
Depth Separable architecture for Sentinel-5P Super-Resolution—0
Show:102550
← PrevPage 29 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified