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 2611–2620 of 3874 papers

TitleStatusHype
Burst Image Super-Resolution via Multi-Cross Attention Encoding and Multi-Scan State-Space Decoding—0
Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessment—0
Building Footprint Extraction in Dense Areas using Super Resolution and Frame Field Learning—0
BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution—0
BUbble Flow Field: a Simulation Framework for Evaluating Ultrasound Localization Microscopy Algorithms—0
Perception-Distortion Trade-off in the SR Space Spanned by Flow Models—0
BSRAW: Improving Blind RAW Image Super-Resolution—0
Perception-Oriented Stereo Image Super-Resolution—0
A CNN-Based Super-Resolution Technique for Active Fire Detection on Sentinel-2 Data—0
Perceptual Deep Neural Networks: Adversarial Robustness through Input Recreation—0
Show:102550
← PrevPage 262 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified