SOTAVerified

Image Super-Resolution

Image Super-Resolution is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 851–875 of 1589 papers

TitleStatusHype
SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-ResolutionCode1
SwiftSRGAN -- Rethinking Super-Resolution for Efficient and Real-time Inference—0
Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reduction—0
A Practical Contrastive Learning Framework for Single-Image Super-ResolutionCode1
Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution—0
AdaDM: Enabling Normalization for Image Super-ResolutionCode1
A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective—0
Local-Selective Feature Distillation for Single Image Super-Resolution—0
FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform—0
Image Super-Resolution Using T-Tetromino Pixels—0
Local Texture Estimator for Implicit Representation FunctionCode1
Image-specific Convolutional Kernel Modulation for Single Image Super-resolutionCode1
A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for Efficient Hyperspectral Image Super-resolution—0
Pansharpening by convolutional neural networks in the full resolution frameworkCode1
GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention—0
Frequency-Aware Physics-Inspired Degradation Model for Real-World Image Super-Resolution—0
Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art—0
Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation—0
Scale-Aware Dynamic Network for Continuous-Scale Super-ResolutionCode1
Improving Super-Resolution Performance using Meta-Attention LayersCode1
Localized Super Resolution for Foreground Images using U-Net and MR-CNNCode0
An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural RepresentationCode1
RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural NetworkCode0
Dense Dual-Attention Network for Light Field Image Super-Resolution—0
Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution—0
Show:102550
← PrevPage 35 of 64Next →
All datasetsSet14 - 4x upscalingBSD100 - 4x upscalingUrban100 - 4x upscalingManga109 - 4x upscalingSet5 - 2x upscalingSet14 - 2x upscalingSet5 - 3x upscalingBSD100 - 2x upscalingUrban100 - 2x upscalingSet14 - 3x upscalingUrban100 - 3x upscalingBSD100 - 3x upscaling

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DRCT-LPSNR29.54—Unverified
2HMA†PSNR29.51—Unverified
3Hi-IR-LPSNR29.49—Unverified
4HAT-LPSNR29.47—Unverified
5HAT_FIRPSNR29.44—Unverified
6DRCTPSNR29.4—Unverified
7HATPSNR29.38—Unverified
8CPAT+PSNR29.36—Unverified
9SwinFIRPSNR29.36—Unverified
10CPATPSNR29.34—Unverified
#ModelMetricClaimedVerifiedStatus
1DRCT-LPSNR28.16—Unverified
2HMA†PSNR28.13—Unverified
3Hi-IR-LPSNR28.13—Unverified
4HAT-LPSNR28.09—Unverified
5HAT_FIRPSNR28.07—Unverified
6CPAT+PSNR28.06—Unverified
7DRCTPSNR28.06—Unverified
8HATPSNR28.05—Unverified
9CPATPSNR28.04—Unverified
10SwinFIRPSNR28.03—Unverified
#ModelMetricClaimedVerifiedStatus
1Hi-IR-LPSNR28.72—Unverified
2DRCT-LPSNR28.7—Unverified
3HMA†PSNR28.69—Unverified
4HAT-LPSNR28.6—Unverified
5HAT_FIRPSNR28.43—Unverified
6DRCTPSNR28.4—Unverified
7HATPSNR28.37—Unverified
8CPAT+PSNR28.33—Unverified
9CPATPSNR28.22—Unverified
10PFTPSNR28.2—Unverified