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 371–380 of 3874 papers

TitleStatusHype
DeblurSR: Event-Based Motion Deblurring Under the Spiking RepresentationCode1
Adaptive Convolutional Neural Network for Image Super-resolutionCode1
A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-ResolutionCode1
A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutionCode1
Decomposition-Based Variational Network for Multi-Contrast MRI Super-Resolution and ReconstructionCode1
Discovering Distinctive "Semantics" in Super-Resolution NetworksCode1
DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRFCode1
LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion ModelCode1
A Tree-guided CNN for image super-resolutionCode1
DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-ResolutionCode1
Show:102550
← PrevPage 38 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified