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 1691–1700 of 3874 papers

TitleStatusHype
Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition—0
Temporal Super-Resolution using Multi-Channel Illumination Source—0
Interactive Image Manipulation with Complex Text Instructions—0
Simulation-based parameter optimization for fetal brain MRI super-resolution reconstruction—0
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image SynthesisCode1
Domain generalization in fetal brain MRI segmentation \ multi-reconstruction augmentation—0
A mathematical theory of resolution limits for super-resolution of positive sources—0
Perception-Oriented Single Image Super-Resolution using Optimal Objective EstimationCode1
GAN Prior based Null-Space Learning for Consistent Super-ResolutionCode1
Immersive Neural Graphics PrimitivesCode2
Show:102550
← PrevPage 170 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified