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 3791–3800 of 3874 papers

TitleStatusHype
FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing FlowCode0
Frequency Separation for Real-World Super-ResolutionCode0
Deep learning-based super-resolution fluorescence microscopy on small datasetsCode0
FOD-Swin-Net: angular super resolution of fiber orientation distribution using a transformer-based deep modelCode0
Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-ResolversCode0
Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation DecodersCode0
Flow-based Visual Quality Enhancer for Super-resolution Magnetic Resonance Spectroscopic ImagingCode0
CoPE: Conditional image generation using Polynomial ExpansionsCode0
ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian SplattingCode0
3DSRnet: Video Super-resolution using 3D Convolutional Neural NetworksCode0
Show:102550
← PrevPage 380 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified