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 1181–1190 of 3874 papers

TitleStatusHype
Guided Frequency Loss for Image Restoration—0
Neural Operators for Accelerating Scientific Simulations and Design—0
LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion ModelsCode1
An Ensemble Model for Distorted Images in Real Scenarios—0
DONNAv2 -- Lightweight Neural Architecture Search for Vision tasks—0
A Lightweight Recurrent Grouping Attention Network for Video Super-ResolutionCode0
Data Upcycling Knowledge Distillation for Image Super-ResolutionCode0
Adaptation of the super resolution SOTA for Art Restoration in camera capture imagesCode0
Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data—0
Cine cardiac MRI reconstruction using a convolutional recurrent network with refinementCode0
Show:102550
← PrevPage 119 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified