A Deep Journey into Super-resolution

By Saeed Anwar, Salman Hameed Khan, Nick Barnes. ACM Computing Surveys, 2019

489 citations recorded by the source corpus.

Deep convolutional networks–based super-resolution is a fast-growing field with numerous practical applications. In this exposition, we extensively compare more than 30 state-of-the-art super-resolution Convolutional Neural Networks (CNNs) over three classical and three recently introduced challenging datasets to benchmark single image super-resolution. We introduce a taxonomy for deep learning–based super-resolution networks that groups existing methods into nine categories including linear, residual, multi-branch, recursive, progressive, attention-based, and adversarial designs. We also provide comparisons between the models in terms of network complexity, memory footprint, model input and output, learning details, the type of network losses, and important architectural differences (e.g., depth, skip-connections, filters). The extensive evaluation performed shows the consistent and rapid growth in the accuracy in the past few years along with a corresponding boost in model complexity and the availability of large-scale datasets. It is also observed that the pioneering methods identified as the benchmarks have been significantly outperformed by the current contenders. Despite the progress in recent years, we identify several shortcomings of existing techniques and provide future research directions towards the solution of these open problems. Datasets and codes for evaluation are publicly available at https://github.com/saeed-anwar/SRsurvey.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/9cbb1214ea82948a71d5dbe60f07c086274f6e26

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Restormer: Efficient Transformer for High-Resolution Image Restoration (2021, methodology): “We refer the reader to NTIRE challenge reports [2,5,30,57] and recent literature reviews [8,42,73], which summarize major design choices for image restoration.”
Multi-Stage Progressive Image Restoration (2021, background): “In contrast, the approaches that operate on single-scale feature pipeline are reliable in generating images with fine spatial details [6, 18, 93, 97].”
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning (2022, methodology): “Following super resolution literature [2], an L1 loss is used for high frequency output to better reconstruct edges and an L2 loss is used for low frequency output to better reconstruct average values.”
Learning Enriched Features for Fast Image Restoration and Enhancement (2022, methodology): “The data-driven SR approaches differ according to their architecture designs [53], [54], [55].”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, methodology): “Here, we compute the PSNR and SSIM scores using the Y channel (in YCbCr color space), as it is a common practice in the SR literature [125,14,106,6].”
Learned Image Downscaling for Upscaling Using Content Adaptive Resampler (2019, methodology): “org) LR version downscaled using traditional filtering-decimation based methods with great performance gain [8, 9].”