Comprehensive Survey on Image Super-resolution using Deep Learning Models

Author(s)	Prof. Pushpalatha H P, Dr. Salila Hegde
Country	India
Abstract	Image Super-Resolution (ISR) is a fundamental computer vision task that aims to reconstruct a high-resolution (HR) image from its corresponding low-resolution (LR) counterpart. Deep Learning has revolutionized this field, dramatically outperforming classical interpolation and model-based methods. This survey provides a structured overview of the deep learning era in ISR, tracing the evolution from pioneering convolutional neural networks (CNNs) to modern generative and transformer-based approaches. We cover key network architectures, key components, loss functions, benchmark datasets, evaluation metrics, current challenges and future directions offering a roadmap for researchers and practitioners. We discuss, benchmark datasets, evaluation metrics, and highlight current challenges and future directions.
Keywords	SRCNN, ESRGAN, Deep learning, up sampling and recursive learning, Attention and Transformer based network
Field	Engineering
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-29
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.63228

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research