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 471–480 of 3874 papers

TitleStatusHype
DL4DS -- Deep Learning for empirical DownScalingCode1
BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder ArchitectureCode1
Face Super-Resolution Using Stochastic Differential EquationsCode1
HRTF upsampling with a generative adversarial network using a gnomonic equiangular projectionCode1
Frequency Domain-based Perceptual Loss for Super ResolutionCode1
BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-ResolutionCode1
DREAM: Diffusion Rectification and Estimation-Adaptive ModelsCode1
Conditional Simulation Using Diffusion Schrödinger BridgesCode1
Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV MinimizationCode1
Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical SystemsCode1
Show:102550
← PrevPage 48 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified