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 151–175 of 3874 papers

TitleStatusHype
Boosting Flow-based Generative Super-Resolution Models via Learned PriorCode2
Exposure Bracketing Is All You Need For A High-Quality ImageCode2
DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration ModelsCode2
Distillation-Free One-Step Diffusion for Real-World Image Super-ResolutionCode2
Effective Diffusion Transformer Architecture for Image Super-ResolutionCode2
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory MatchingCode2
Enhancing Video Super-Resolution via Implicit Resampling-based AlignmentCode2
AERO: Audio Super Resolution in the Spectral DomainCode2
Denoising Diffusion Models for Plug-and-Play Image RestorationCode2
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution PriorsCode2
Denoising Diffusion Restoration ModelsCode2
CogView2: Faster and Better Text-to-Image Generation via Hierarchical TransformersCode2
AIM 2020 Challenge on Efficient Super-Resolution: Methods and ResultsCode2
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-ResolutionCode2
Arbitrary-Scale Video Super-Resolution with Structural and Textural PriorsCode2
Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel FusionCode2
CFAT: Unleashing Triangular Windows for Image Super-resolutionCode2
CFAT: Unleashing TriangularWindows for Image Super-resolutionCode2
HSIGene: A Foundation Model For Hyperspectral Image GenerationCode2
I^2SB: Image-to-Image Schrödinger BridgeCode2
Image Super-Resolution Using Very Deep Residual Channel Attention NetworksCode2
Immersive Neural Graphics PrimitivesCode2
CoSeR: Bridging Image and Language for Cognitive Super-ResolutionCode2
Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-ResolutionCode2
Deep Constrained Least Squares for Blind Image Super-ResolutionCode2
Show:102550
← PrevPage 7 of 155Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified