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 2771–2780 of 3874 papers

TitleStatusHype
ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-ResolutionCode0
Unfolding the Alternating Optimization for Blind Super ResolutionCode1
AFN: Attentional Feedback Network based 3D Terrain Super-ResolutionCode0
Spatial Frequency Bias in Convolutional Generative Adversarial Networks—0
Efficient Image Super-Resolution Using Pixel AttentionCode1
High Quality Remote Sensing Image Super-Resolution Using Deep Memory Connected Network—0
Deformable Kernel Convolutional Network for Video Extreme Super-Resolution—0
FAN: Frequency Aggregation Network for Real Image Super-resolution—0
AIM 2020 Challenge on Video Temporal Super-Resolution—0
High-throughput molecular imaging via deep learning enabled Raman spectroscopyCode1
Show:102550
← PrevPage 278 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified