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

Showing 12761300 of 3874 papers

TitleStatusHype
Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse CodingCode0
Maintaining Natural Image Statistics with the Contextual LossCode0
Localized Super Resolution for Foreground Images using U-Net and MR-CNNCode0
Criteria Comparative Learning for Real-scene Image Super-ResolutionCode0
A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial ImageryCode0
Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-ResolutionCode0
MemNet: A Persistent Memory Network for Image RestorationCode0
A Fusion-Guided Inception Network for Hyperspectral Image Super-ResolutionCode0
Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-ResolutionCode0
Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-ResolversCode0
A Cone-Beam X-Ray CT Data Collection designed for Machine LearningCode0
CoPE: Conditional image generation using Polynomial ExpansionsCode0
A Fully Progressive Approach to Single-Image Super-ResolutionCode0
Lightweight and Robust Representation of Economic Scales from Satellite ImageryCode0
Lightweight Feature Fusion Network for Single Image Super-ResolutionCode0
Lightweight and Efficient Image Super-Resolution with Block State-based Recursive NetworkCode0
Lightweight Image Super-Resolution with Adaptive Weighted Learning NetworkCode0
ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian SplattingCode0
A Self-Supervised Deep Denoiser for Hyperspectral and Multispectral Image FusionCode0
Leveraging Segment Anything Model in Identifying Buildings within Refugee Camps (SAM4Refugee) from Satellite Imagery for Humanitarian OperationsCode0
ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-ResolutionCode0
Learning to Super Resolve Intensity Images from EventsCode0
Continual Learning Approaches for Anomaly DetectionCode0
Handheld Multi-Frame Super-ResolutionCode0
Learning Parallax Attention for Stereo Image Super-ResolutionCode0
Show:102550
← PrevPage 52 of 155Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1super-resolutionAverage PSNR20.41Unverified