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 911–920 of 3874 papers

TitleStatusHype
ODVista: An Omnidirectional Video Dataset for super-resolution and Quality Enhancement TasksCode1
Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of ArtifactsCode2
SeD: Semantic-Aware Discriminator for Image Super-ResolutionCode2
LoLiSRFlow: Joint Single Image Low-light Enhancement and Super-resolution via Cross-scale Transformer-based Conditional Flow—0
Unsupervised Learning of High-resolution Light Field Imaging via Beam Splitter-based Hybrid Lenses—0
Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution—0
CAMixerSR: Only Details Need More "Attention"Code3
Misalignment-Robust Frequency Distribution Loss for Image TransformationCode2
Self-Supervised Learning with Generative Adversarial Networks for Electron Microscopy—0
Simple Base Frame Guided Residual Network for RAW Burst Image Super-ResolutionCode1
Show:102550
← PrevPage 92 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified