Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances

Abstract

With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics. We review the domain of SR in light of recent advances, and examine state-of-the-art models such as diffusion (DDPM) and transformer-based SR models. We present a critical discussion on contemporary strategies used in SR, and identify promising yet unexplored research directions. We complement previous surveys by incorporating the latest developments in the field such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the latests evaluation techniques. We also include several visualizations for the models and methods throughout each chapter in order to facilitate a global understanding of the trends in the field. This review is ultimately aimed at helping researchers to push the boundaries of DL applied to SR.

accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Denoising Diffusion Probabilistic Models
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Lightweight Image Super-Resolution with Information Multi-distillation Network
• Image Quality Assessment: Unifying Structure and Texture Similarity
• Gated Feedback Recurrent Neural Networks
• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs
• Adversarial Text-to-Image Synthesis: A Review
• Is the deconvolution layer the same as a convolutional layer?
• SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
• Structure-Preserving Image Super-resolution via Contextualized Multi-task Learning
• Hierarchical Neural Architecture Search for Single Image Super-Resolution
• Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution
• AdaDM: Enabling Normalization for Image Super-Resolution
• Attention-based Image Upsampling

Cited by in corpus (7)

• Diffusion Models, Image Super-Resolution And Everything: A Survey
• UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration
• Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution
• DWA: Differential Wavelet Amplifier for Image Super-Resolution
• Dynamic Attention-Guided Diffusion for Image Super-Resolution
• Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
• Embedding Similarity Guided License Plate Super Resolution