Real-Time Super Resolution Utilizing Dilation and Depthwise Separable Convolution
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 ne...
Saved in:
Main Authors: | Che-Cheng Chang, Wen-Pin Chen, Yi-Wei Lin, Yu-Jhan Lin, Po-Jui Pan |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-04-01
|
Series: | Engineering Proceedings |
Subjects: | |
Online Access: | https://www.mdpi.com/2673-4591/92/1/27 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions
by: Mustafa Ghaleb, et al.
Published: (2025-01-01) -
Rolling Bearing Fault Diagnosis Model Based on Multi-Scale Depthwise Separable Convolutional Neural Network Integrated with Spatial Attention Mechanism
by: Zhixin Jin, et al.
Published: (2025-06-01) -
Fault Diagnosis Method for Shearer Arm Gear Based on Improved S-Transform and Depthwise Separable Convolution
by: Haiyang Wu, et al.
Published: (2025-06-01) -
Utilizing GCN-Based Deep Learning for Road Extraction from Remote Sensing Images
by: Yu Jiang, et al.
Published: (2025-06-01) -
LSANet: Lightweight Super Resolution via Large Separable Kernel Attention for Edge Remote Sensing
by: Tingting Yong, et al.
Published: (2025-07-01)