Deep Learning for Image Super-Resolution: A Survey

2020/03/23 by Zhihao Wang, Jian Chen, Steven C. H. Hoi · 64 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Image Processing Techniques and Applications #Image and Signal Denoising Methods

paper · doi:10.1109/tpami.2020.2982166

openalex publication_date 2020/03/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Image Super-Resolution (SR) is an important class of image processing techniqueso enhance the resolution of images and videos in computer vision. Recent years have witnessed remarkable progress of image super-resolution using deep learning techniques. This article aims to provide a comprehensive survey on recent advances of image super-resolution using deep learning approaches. In general, we can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR. In addition, we also cover some other important issues, such as publicly available benchmark datasets and performance evaluation metrics. Finally, we conclude this survey by highlighting several future directions and open issues which should be further addressed by the community in the future.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures
• Super-Resolution in Medical Imaging
• Lanczos Filtering in One and Two Dimensions
• Super-resolution image reconstruction: a technical overview
• Screenings in the rain
• A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms
• Amortised MAP Inference for Image Super-resolution
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• NIMA: Neural Image Assessment
• The Perception-Distortion Tradeoff
• Spectral Normalization for Generative Adversarial Networks
• DARTS: Differentiable Architecture Search
• Residual Non-local Attention Networks for Image Restoration
• Conditional Image Generation with PixelCNN Decoders
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Generative Adversarial Nets

Cited by

• Attention in Attention Network for Image Super-Resolution
• Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
• Uformer: A General U-Shaped Transformer for Image Restoration
• Cascade Convolutional Neural Network for Image Super-Resolution
• SRF-GAN: Super-Resolved Feature GAN for Multi-Scale Representation
• A Versatile Framework for Designing Group-Sparse Adversarial Attacks
• An Efficient Remote Sensing Super Resolution Method Exploring Diffusion Priors and Multi-Modal Constraints for Crop Type Mapping
• A Comprehensive Review of Deep Learning-based Single Image Super-resolution
• Uformer: A General U-Shaped Transformer for Image Restoration
• Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution
• CATformer: Contrastive Adversarial Transformer for Image Super-Resolution
• Super-resolution reconstruction of turbulent flows from a single Lagrangian trajectory
• OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution
• Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
• EatGAN: An Edge-Attention Guided Generative Adversarial Network for Single Image Super-Resolution
• TTSR: A Transformer-Based Topography Neural Network for Digital Elevation Model Super-Resolution
• Efficient Image Super-Resolution Using Pixel Attention
• Your Super Resolution Model is not Enough for Tackling Real-World Scenarios
• Multidimensional Distributional Neural Network Output Demonstrated in Super-Resolution of Surface Wind Speed
• Potential and challenges of generative adversarial networks for super-resolution in 4D Flow MRI
• CD-TVD: Contrastive Diffusion for 3D Super-Resolution with Scarce High-Resolution Time-Varying Data
• OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution
• Rotation Equivariant Arbitrary-scale Image Super-Resolution
• Exploiting Aliasing for Manga Restoration
• DEM Super-Resolution with EfficientNetV2
• SuperMag: Vision-based Tactile Data Guided High-resolution Tactile Shape Reconstruction for Magnetic Tactile Sensors
• GPSMamba: A Global Phase and Spectral Prompt-guided Mamba for Infrared Image Super-Resolution
• BAM: A Balanced Attention Mechanism for Single Image Super Resolution
• Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization
• Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
• Super-resolving Compressed Images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement
• Improving axial resolution in SIM using deep learning
• MAMBO: High-Resolution Generative Approach for Mammography Images
• Controllable Reference Guided Diffusion with Local Global Fusion for Real World Remote Sensing Image Super Resolution
• Metadata, Wavelet, and Time Aware Diffusion Models for Satellite Image Super Resolution
• Task-driven real-world super-resolution of document scans
• Enhancing Frequency for Single Image Super-Resolution with Learnable Separable Kernels
• Deep Metric Learning Model for Imbalanced Fault Diagnosis
• Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation
• SAAT: Synergistic Alternating Aggregation Transformer for Image Super-Resolution
• A Survey of Deep Learning Video Super-Resolution
• One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillation
• A Tree-guided CNN for image super-resolution
• Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey
• Single Image Super-resolution with a Switch Guided Hybrid Network for Satellite Images
• Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
• BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
• Stochastic Orthogonal Regularization for deep projective priors
• CLIP-aware Domain-Adaptive Super-Resolution
• Improving regional weather forecasts with neural interpolation
• Unpaired Downscaling of Fluid Flows with Diffusion Bridges
• PixelSR: Efficient Screen Content Super-Resolution via Pixel Classification
• Attention-based Image Upsampling
• Deep Learning-based Face Super-Resolution: A Survey
• Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution
• More Reliable AI Solution: Breast Ultrasound Diagnosis Using Multi-AI Combination
• Blind Image Super-Resolution with Spatial Context Hallucination
• Deep Reinforcement Learning for Automated Web GUI Testing
• S³-Diff: Structural Semantic Synergy Diffusion Model for High Fidelity Super Resolution of Pathological Images
• Active fire detection in Landsat-8 imagery: A large-scale dataset and a deep-learning study
• Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact
• Resampling and super-resolution of hexagonally sampled images using deep learning
• Small Object Detection with YOLO: A Performance Analysis Across Model Versions and Hardware
• DeepSMCP – Deep-learning powered denoising of Monte Carlo dose distributions within the Swiss Monte Carlo Plan

Related

• Deep Learning for Image Super-resolution: A Survey
• Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
• A Comprehensive Review of Deep Learning-based Single Image Super-resolution
• A Systematic Survey of Deep Learning-based Single-Image Super-Resolution
• A Review of Deep Learning Based Image Super-resolution Techniques