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 111–120 of 3874 papers

TitleStatusHype
Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-ResolutionCode2
SRGS: Super-Resolution 3D Gaussian SplattingCode2
Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differencesCode2
Rethinking Diffusion Model for Multi-Contrast MRI Super-ResolutionCode2
AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-ResolutionCode2
GenN2N: Generative NeRF2NeRF TranslationCode2
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion DistillationCode2
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual LossCode2
Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion ModelCode2
CFAT: Unleashing TriangularWindows for Image Super-resolutionCode2
Show:102550
← PrevPage 12 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified