TMSR: Tiny Multi-path CNNs for Super Resolution

Chia Hung Liu, Tzu Hsin Hsieh, Kuan Yu Huang, Pei Yin Chen

研究成果: Conference contribution

摘要

We proposed a tiny multi-path CNN-based Super-Resolution (SR) method (TMSR) referring to tiny CNN-based SR methods under 5k parameters. The main contribution of the proposed method is the improved multi-path learning. The experimental results showed that TMSR obtained competitive image quality (peak-signal-to-noise ratio and Structural Similarity Index Measure) compared to the related works under 5k parameters.

原文English
主出版物標題2023 IEEE 5th Eurasia Conference on IOT, Communication and Engineering, ECICE 2023
編輯Teen-Hang Meen
發行者Institute of Electrical and Electronics Engineers Inc.
頁面829-833
頁數5
ISBN(電子)9798350314694
DOIs
出版狀態Published - 2023
事件5th IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2023 - Yunlin, Taiwan
持續時間: 2023 10月 272023 10月 29

出版系列

名字2023 IEEE 5th Eurasia Conference on IOT, Communication and Engineering, ECICE 2023

Conference

Conference5th IEEE Eurasia Conference on IOT, Communication and Engineering, ECICE 2023
國家/地區Taiwan
城市Yunlin
期間23-10-2723-10-29

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 電腦科學應用
  • 電腦視覺和模式識別
  • 硬體和架構
  • 人機介面
  • 媒體技術

指紋

深入研究「TMSR: Tiny Multi-path CNNs for Super Resolution」主題。共同形成了獨特的指紋。

引用此