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 641–650 of 3874 papers

TitleStatusHype
Deep Unfolding Network for Image Super-ResolutionCode1
DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional FlowsCode1
AeroRIT: A New Scene for Hyperspectral Image AnalysisCode1
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution ModelsCode1
Fast Monte Carlo Rendering via Multi-Resolution SamplingCode1
Computing Multiple Image Reconstructions with a Single HypernetworkCode1
DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-ResolutionCode1
CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image GenerationCode1
Feature Distillation Interaction Weighting Network for Lightweight Image Super-ResolutionCode1
Deep Reparametrization of Multi-Frame Super-Resolution and DenoisingCode1
Show:102550
← PrevPage 65 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified