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 741–750 of 3874 papers

TitleStatusHype
Thermal Image Processing via Physics-Inspired Deep NetworksCode1
spectrai: A deep learning framework for spectral dataCode1
Light Field Image Super-Resolution with TransformersCode1
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image RescalingCode1
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-ResolutionCode1
Finding Discriminative Filters for Specific Degradations in Blind Super-ResolutionCode1
Discovering Distinctive "Semantics" in Super-Resolution NetworksCode1
Fourier Series Expansion Based Filter Parametrization for Equivariant ConvolutionsCode1
Crack Segmentation for Low-Resolution Images using Joint Learning with Super-ResolutionCode1
Self-Conditioned Probabilistic Learning of Video RescalingCode1
Show:102550
← PrevPage 75 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified