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 1231–1240 of 3874 papers

TitleStatusHype
The Power of Context: How Multimodality Improves Image Super-Resolution—0
SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion Model—0
A super-resolution reconstruction method for lightweight building images based on an expanding feature modulation network—0
RainScaleGAN: a Conditional Generative Adversarial Network for Rainfall DownscalingCode0
Rethinking Image Evaluation in Super-Resolution—0
C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales—0
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video—0
Fourier Neural Operator based surrogates for CO_2 storage in realistic geologies—0
ECLARE: Efficient cross-planar learning for anisotropic resolution enhancementCode0
Dual-domain Modulation Network for Lightweight Image Super-Resolution—0
Show:102550
← PrevPage 124 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified