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 21–30 of 3874 papers

TitleStatusHype
EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense PredictionCode4
NAFSSR: Stereo Image Super-Resolution Using NAFNetCode4
High-Resolution Image Synthesis with Latent Diffusion ModelsCode4
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic DataCode4
Event-Enhanced Blurry Video Super-ResolutionCode3
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge ReportCode3
CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-ResolutionCode3
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory DistillationCode3
TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-ResolutionCode3
General Geospatial Inference with a Population Dynamics Foundation ModelCode3
Show:102550
← PrevPage 3 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified