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

Showing 451500 of 1589 papers

TitleStatusHype
Residual Feature Distillation Network for Lightweight Image Super-ResolutionCode1
GSR-Net: Graph Super-Resolution Network for Predicting High-Resolution from Low-Resolution Functional Brain ConnectomesCode1
Parallax Attention for Unsupervised Stereo Correspondence LearningCode1
Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter EstimationCode1
Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-ResolutionCode1
MDCN: Multi-scale Dense Cross Network for Image Super-ResolutionCode1
Multi-Attention Based Ultra Lightweight Image Super-ResolutionCode1
Deep Variational Network Toward Blind Image RestorationCode1
Single Image Super-Resolution via a Holistic Attention NetworkCode1
Component Divide-and-Conquer for Real-World Image Super-ResolutionCode1
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANCode1
Sub-Pixel Back-Projection Network For Lightweight Single Image Super-ResolutionCode1
Spatial-Angular Interaction for Light Field Image Super-ResolutionCode1
Multi-Step Reinforcement Learning for Single Image Super-ResolutionCode1
Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent NetworksCode1
Frequency Domain-based Perceptual Loss for Super ResolutionCode1
Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-ResolutionCode1
Lightweight image super-resolution with enhanced CNNCode1
Light Field Image Super-Resolution Using Deformable ConvolutionCode1
Multi-image Super Resolution of Remotely Sensed Images using Residual Feature Attention Deep Neural NetworksCode1
Cross-Scale Internal Graph Neural Network for Image Super-ResolutionCode1
SRFlow: Learning the Super-Resolution Space with Normalizing FlowCode1
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection NetworksCode1
Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual LearningCode1
Exploring Sparsity in Image Super-Resolution for Efficient InferenceCode1
iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networksCode1
Neural Sparse Representation for Image RestorationCode1
Learning Texture Transformer Network for Image Super-ResolutionCode1
Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars MiningCode1
Dual Super-Resolution Learning for Semantic SegmentationCode1
Robust Reference-Based Super-Resolution With Similarity-Aware Deformable ConvolutionCode1
Perceptual Extreme Super Resolution Network with Receptive Field BlockCode1
Iterative Network for Image Super-ResolutionCode1
Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral ImageryCode1
Invertible Image RescalingCode1
HiFaceGAN: Face Renovation via Collaborative Suppression and ReplenishmentCode1
Scene Text Image Super-Resolution in the WildCode1
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and ResultsCode1
Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-ResolutionCode1
Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoderCode1
Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-AttentionCode1
Learning A Single Network for Scale-Arbitrary Super-ResolutionCode1
Deep Adaptive Inference Networks for Single Image Super-ResolutionCode1
Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood EstimationCode1
Unsupervised Real-world Image Super Resolution via Domain-distance Aware TrainingCode1
Robust Single-Image Super-Resolution via CNNs and TV-TV MinimizationCode1
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New StrategyCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Structure-Preserving Super Resolution with Gradient GuidanceCode1
Deep Unfolding Network for Image Super-ResolutionCode1
Show:102550
← PrevPage 10 of 32Next →

Benchmark Results

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