arrow
返回

Asymmetric convolutional modulation network for efficient image super-resolution

delete2024-10-01
delete0
PRE
AI
F
Feng Xie
路
路培 (Pei Lü) *
刘
刘小勇 (Xiaoyong Liu)
DOI:10.1016/j.knosys.2024.112274delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Thanks to the effectiveness of large kernel convolutions in acquiring large receptive fields, lightweight single image super-resolution (SISR) approaches based on large kernel designs have achieved significant performance. However, these state-of-the-art methods still require high computational costs, and their model efficiency remains to be improved. To address these challenges, we propose an asymmetric convolutional modulation network (ACMN) for efficient image super-resolution. In detail, we design an asymmetric convolutional modulation unit (ACMU) that combines large kernel design and modulation mechanism for adaptively selecting representative features from a large receptive field. Furthermore, we adopt depth-wise asymmetric convolutions to further reduce computational burden. To supplement the local context information and promote inter- channel interaction, we further develop a channel shuffle feedforward network (CSFN) to extract local feature information and facilitate inter-channel information interaction. Experimental results demonstrate that our ACMN outperforms other state-of-the-art efficient SR methods with fewer parameters and Multi-Adds.
Keyword:
Single image super-resolution
Efficient network
Large kernel design
Asymmetric convolution
Convolutional modulation

期刊

K
Knowledge-Based Systems
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

G
Guilin University of Technology
学者数:
9.3K
论文数: 5.5K
被引数: 6.8K
引用论文

引用论文

LKASR: Large kernel attention for lightweight image super-resolution
err2022-09-01
err26
PREAI
errFeng, Hao; Wang, Liejun; Li, Yongming; Du, Anyu
err分享
err收藏
err分享
err收藏
Lightweight blueprint residual network for single image super-resolution
err2024-09-01
err3
PREAI
errHao, Fangwei; Wu, Jiesheng; Liang, Weiyun; Xu, Jing; Li, Ping
err分享
err收藏
学者 查看更多内容