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 871–880 of 3874 papers

TitleStatusHype
Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-ResolutionCode0
Residual Dense Swin Transformer for Continuous Depth-Independent Ultrasound ImagingCode1
LaMAR: Laplacian Pyramid for Multimodal Adaptive Super Resolution (Student Abstract)—0
CFAT: Unleashing TriangularWindows for Image Super-resolutionCode2
Adaptive Super Resolution For One-Shot Talking-Head GenerationCode2
Time-series Initialization and Conditioning for Video-agnostic Stabilization of Video Super-Resolution using Recurrent Networks—0
Deep Generative Model based Rate-Distortion for Image Downscaling AssessmentCode0
Hyperspectral Neural Radiance Fields—0
QSMDiff: Unsupervised 3D Diffusion Models for Quantitative Susceptibility Mapping—0
Using Super-Resolution Imaging for Recognition of Low-Resolution Blurred License Plates: A Comparative Study of Real-ESRGAN, A-ESRGAN, and StarSRGAN—0
Show:102550
← PrevPage 88 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified