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 881–890 of 3874 papers

TitleStatusHype
Efficient scene text image super-resolution with semantic guidanceCode1
A Wideband Distributed Massive MIMO Channel Sounder for Communication and Sensing—0
PAON: A New Neuron Model using Padé Approximants—0
VmambaIR: Visual State Space Model for Image RestorationCode3
CasSR: Activating Image Power for Real-World Image Super-Resolution—0
Adaptive Semantic-Enhanced Denoising Diffusion Probabilistic Model for Remote Sensing Image Super-ResolutionCode1
Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-ResolutionCode1
Boosting Flow-based Generative Super-Resolution Models via Learned PriorCode2
A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models—0
BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-ResolutionCode1
Show:102550
← PrevPage 89 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified