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 1871–1880 of 3874 papers

TitleStatusHype
Emu Edit: Precise Image Editing via Recognition and Generation Tasks—0
DSR-Diff: Depth Map Super-Resolution with Diffusion ModelCode0
RBPGAN: Recurrent Back-Projection GAN for Video Super Resolution—0
Texture and Noise Dual Adaptation for Infrared Image Super-ResolutionCode0
Uni-COAL: A Unified Framework for Cross-Modality Synthesis and Super-Resolution of MR ImagesCode0
The Perception-Robustness Tradeoff in Deterministic Image Restoration—0
Learning based Deep Disentangling Light Field Reconstruction and Disparity Estimation Application—0
Plasma Surrogate Modelling using Fourier Neural Operators—0
Improved Pothole Detection Using YOLOv7 and ESRGANCode0
OW-SLR: Overlapping Windows on Semi-Local Region for Image Super-ResolutionCode0
Show:102550
← PrevPage 188 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified