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 51–75 of 3874 papers

TitleStatusHype
Activating More Pixels in Image Super-Resolution TransformerCode3
ESRGAN: Enhanced Super-Resolution Generative Adversarial NetworksCode3
Blind Image Restoration via Fast Diffusion InversionCode3
Degradation-Guided One-Step Image Super-Resolution with Diffusion PriorsCode3
Event-Enhanced Blurry Video Super-ResolutionCode3
General Geospatial Inference with a Population Dynamics Foundation ModelCode3
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory DistillationCode3
Effective Diffusion Transformer Architecture for Image Super-ResolutionCode2
Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-ResolutionCode2
EAMamba: Efficient All-Around Vision State Space Model for Image RestorationCode2
AIM 2020 Challenge on Efficient Super-Resolution: Methods and ResultsCode2
Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion ModelsCode2
Dual Aggregation Transformer for Image Super-ResolutionCode2
Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-ResolutionCode2
Arbitrary-Scale Video Super-Resolution with Structural and Textural PriorsCode2
DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-ResolutionCode2
DVMSR: Distillated Vision Mamba for Efficient Super-ResolutionCode2
Efficient Face Super-Resolution via Wavelet-based Feature Enhancement NetworkCode2
Diffusion Models for Image Restoration and Enhancement -- A Comprehensive SurveyCode2
DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration ModelsCode2
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse ProblemsCode2
AEROMamba: An efficient architecture for audio super-resolution using generative adversarial networks and state space modelsCode2
DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-ResolutionCode2
A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-ResolutionCode2
AERO: Audio Super Resolution in the Spectral DomainCode2
Show:102550
← PrevPage 3 of 155Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified