Comprehensive Review of Deep Learning Approaches for Single-Image Super-Resolution

Liu, Zirun; Jiang, Shijie; Feng, Shuhan; Song, Qirui; Zhang, Ji

doi:10.3390/s25185768

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessReview

Comprehensive Review of Deep Learning Approaches for Single-Image Super-Resolution

by

Zirun Liu

^1,2,†,

Shijie Jiang

^3,†,

Shuhan Feng

³,

Qirui Song

³ and

Ji Zhang

^1,3,*

¹

Harbin Institute of Technology, School of Architecture and Design, Harbin 150001, China

²

Longmen Laboratory, Henan University of Science and Technology, Luoyang 471000, China

³

School of Information Engineering, Henan University of Science and Technology, Luoyang 471000, China

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Sensors 2025, 25(18), 5768; https://doi.org/10.3390/s25185768

Submission received: 25 August 2025 / Revised: 10 September 2025 / Accepted: 13 September 2025 / Published: 16 September 2025

(This article belongs to the Special Issue Advanced Sensors for Intelligent Robotic Systems: Vision, Touch, and Dexterous Manipulation)

Download Versions Notes

Abstract

Single-image super-resolution (SISR) is a core challenge in the field of image processing, aiming to overcome the physical limitations of imaging systems and improve their resolution. This article systematically introduces the SISR method based on deep learning, proposes a method-oriented classification framework, and explores it from three aspects: theoretical basis, technological evolution, and domain-specific applications. Firstly, the basic concepts, development trajectory, and practical value of SISR are introduced. Secondly, in-depth research is conducted on key technical components, including benchmark dataset construction, a multi-scale upsampling strategy, objective function optimization, and quality assessment indicators. Thirdly, some classic SISR model reconstruction results are listed and compared. Finally, the limitations of SISR research are pointed out, and some prospective research directions are proposed. This article provides a systematic knowledge framework for researchers and offers important reference value for the future development of SISR.

Keywords: single-image super-resolution; deep learning; image quality assessment

Share and Cite

MDPI and ACS Style

Liu, Z.; Jiang, S.; Feng, S.; Song, Q.; Zhang, J. Comprehensive Review of Deep Learning Approaches for Single-Image Super-Resolution. Sensors 2025, 25, 5768. https://doi.org/10.3390/s25185768

AMA Style

Liu Z, Jiang S, Feng S, Song Q, Zhang J. Comprehensive Review of Deep Learning Approaches for Single-Image Super-Resolution. Sensors. 2025; 25(18):5768. https://doi.org/10.3390/s25185768

Chicago/Turabian Style

Liu, Zirun, Shijie Jiang, Shuhan Feng, Qirui Song, and Ji Zhang. 2025. "Comprehensive Review of Deep Learning Approaches for Single-Image Super-Resolution" Sensors 25, no. 18: 5768. https://doi.org/10.3390/s25185768

APA Style

Liu, Z., Jiang, S., Feng, S., Song, Q., & Zhang, J. (2025). Comprehensive Review of Deep Learning Approaches for Single-Image Super-Resolution. Sensors, 25(18), 5768. https://doi.org/10.3390/s25185768

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Comprehensive Review of Deep Learning Approaches for Single-Image Super-Resolution

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI