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 691–700 of 3874 papers

TitleStatusHype
Reflash Dropout in Image Super-ResolutionCode1
On Efficient Transformer-Based Image Pre-training for Low-Level VisionCode1
A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net DiscriminatorsCode1
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image RecognitionCode1
Stable Long-Term Recurrent Video Super-ResolutionCode1
Feature Distillation Interaction Weighting Network for Lightweight Image Super-ResolutionCode1
Text Gestalt: Stroke-Aware Scene Text Image Super-ResolutionCode1
Implicit Transformer Network for Screen Content Image Continuous Super-ResolutionCode1
Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical FlowCode1
A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-ResolutionCode1
Show:102550
← PrevPage 70 of 388Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41—Unverified