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 401–410 of 3874 papers

TitleStatusHype
Edge and Identity Preserving Network for Face Super-ResolutionCode1
LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion ModelCode1
Edge-enhanced Feature Distillation Network for Efficient Super-ResolutionCode1
EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-ResolutionCode1
A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-ResolutionCode1
EBSR: Feature Enhanced Burst Super-Resolution With Deformable AlignmentCode1
Deep Diversity-Enhanced Feature Representation of Hyperspectral ImagesCode1
Automatic quality control in multi-centric fetal brain MRI super-resolution reconstructionCode1
Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark EstimationCode1
Compression-Aware Video Super-ResolutionCode1
Show:102550
← PrevPage 41 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified