EMAF-Net: An Edge-Aware Super-Resolution Framework for Enhanced Object Detection and Semantic Annotation
Open Access
- 26 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 47467-47484
Abstract
Low-resolution image acquisition remains a fundamental bottleneck in real-world vision systems, including surveillance, UAV monitoring, autonomous navigation, and medical imaging, where degraded inputs significantly impair object detection and semantic annotation accuracy. While modern deep learning-based super-resolution (SR) techniques have achieved high reconstruction fidelity in terms of PSNR and SSIM, most existing approaches optimize primarily for perceptual quality without explicitly validating improvements in downstream detection performance. Consequently, a gap persists between low-level image enhancement and high-level semantic reliability. To bridge this gap, we propose EMAF-Net, an Edge-Aware MAXIM Attention Fusion Network that integrates edge-aware SRCNN enrichment, MAXIM-based denoising, lightweight squeeze-and-excitation attention, and multi-scale feature fusion within an adaptive training framework. The architecture is explicitly designed to preserve structural boundaries and semantic consistency required for robust object detection. Unlike conventional SR pipelines, EMAF-Net evaluates enhancement quality not only through reconstruction metrics but also through annotation performance using YOLOv8 on manually curated object labels. Experimental results on the DIV2K dataset demonstrate that EMAF-Net achieves a peak PSNR of 44.10 dB and SSIM of 0.9965, while improving detection performance on super-resolved images to 0.79 precision, 0.69 recall, and 0.68 mIoU. The proposed framework consistently enhances detection reliability under degraded conditions, demonstrating that task-aware super-resolution can effectively align perceptual reconstruction with semantic objectives. These findings position EMAF-Net as a unified enhancement-annotation framework suitable for deployment in real-time vision systems where both image fidelity and detection robustness are critical.Keywords
This publication has 22 references indexed in Scilit:
- A Comprehensive Study On Underwater Object Detection Using Deep Neural NetworksIEEE Access, 2025
- SSCD-YOLO: Semi-Supervised Cross-Domain YOLOv8 for Pedestrian Detection in Low-Light ConditionsIEEE Access, 2025
- Research on UAV Image Road Recognition Application Based on Improved SRCNN2024
- Super-resolution reconstruction of infrared images based on convolutional neural network2024
- Object Detection Using ESRGAN With a Sequential Transfer Learning on Remote Sensing Embedded SystemsIEEE Access, 2024
- Enhancing Image Annotation With Object Tracking and Image Retrieval: A Systematic ReviewIEEE Access, 2024
- PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report2019
- NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results2018
- NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results2017
- NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study2017