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 3831–3840 of 3874 papers

TitleStatusHype
Scale Guided Hypernetwork for Blind Super-Resolution Image Quality AssessmentCode0
Conditioning and Sampling in Variational Diffusion Models for Speech Super-ResolutionCode0
Conditional Generation Using Polynomial ExpansionsCode0
FCSR-GAN: Joint Face Completion and Super-resolution via Multi-task LearningCode0
Scaling Laws For Deep Learning Based Image ReconstructionCode0
3DAttGAN: A 3D Attention-based Generative Adversarial Network for Joint Space-Time Video Super-ResolutionCode0
The Effects of Super-Resolution on Object Detection Performance in Satellite ImageryCode0
FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-ResolutionCode0
FC^2N: Fully Channel-Concatenated Network for Single Image Super-ResolutionCode0
Scene Text Image Super-Resolution via Parallelly Contextual Attention NetworkCode0
Show:102550
← PrevPage 384 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified