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 821–830 of 3874 papers

TitleStatusHype
Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolutionCode1
OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model—0
The Ninth NTIRE 2024 Efficient Super-Resolution Challenge ReportCode3
SRGS: Super-Resolution 3D Gaussian SplattingCode2
NTIRE 2024 Challenge on Image Super-Resolution (4): Methods and ResultsCode1
MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution—0
Super-resolution of biomedical volumes with 2D supervision—0
Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differencesCode2
Differentiable Search for Finding Optimal Quantization Strategy—0
Unfolding ADMM for Enhanced Subspace Clustering of Hyperspectral ImagesCode0
Show:102550
← PrevPage 83 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified