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 831–840 of 3874 papers

TitleStatusHype
LIPT: Latency-aware Image Processing TransformerCode1
Dynamic Deep Learning Based Super-Resolution For The Shallow Water Equations—0
Diffusion-Based Point Cloud Super-Resolution for mmWave Radar Data—0
Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures—0
Space-Time Video Super-resolution with Neural Operator—0
Rethinking Diffusion Model for Multi-Contrast MRI Super-ResolutionCode2
CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data—0
Efficient Learnable Collaborative Attention for Single Image Super-Resolution—0
Gull: A Generative Multifunctional Audio Codec—0
Collaborative Feedback Discriminative Propagation for Video Super-ResolutionCode1
Show:102550
← PrevPage 84 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified