Real-Time Super Resolution Utilizing Dilation and Depthwise Separable Convolution
Open Access
- 28 April 2025
- conference paper
- Published by MDPI AG in Engineering Proceedings
- Vol. 92 (1) , 27
Abstract
Computer vision applications require high-quality reproductions of original images, typically demanding complex models with many trainable parameters and floating-point operations. This increases computational load and restricts deployment on resource-constrained devices. Therefore, we designed a new dilation depthwise super-resolution (DDSR) model that is composed of dilation convolution, depthwise separable convolution, and residual connection, to overcome the predicaments. Compared with the well-known model, fast super-resolution convolutional neural network (FSRCNN), the developed DDSR shows better performance in evaluations and You Only Look Once (YOLO v8) confidence scores. Most importantly, the architecture of the developed DDSR has 55% trainable parameters, 19% floating-point operations per second (FLOPs) of one-channel FSRCNN, 27% of the trainable parameters, and 8% of the FLOPs of three-channel FSRCNN.Keywords
Funding Information
- National Science and Technology Council (112-2221-E-035-062-MY3)
This publication has 7 references indexed in Scilit:
- A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NASMachine Learning and Knowledge Extraction, 2023
- A comprehensive survey on gait analysis: History, parameters, approaches, pose estimation, and future workArtificial Intelligence in Medicine, 2022
- Accelerating the Super-Resolution Convolutional Neural Network2016
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014
- Learning a Deep Convolutional Network for Image Super-Resolution2014
- Understanding and simplifying the structural similarity metric2008