计算机科学
计算机视觉
人工智能
图像(数学)
卷积(计算机科学)
图像处理
算法
噪音(视频)
特征(语言学)
图像压缩
模式识别(心理学)
图像质量
边缘检测
数学
过程(计算)
图像分割
作者
Ruobing Zuo,Liangyu Chen,Zhengfeng Yang
标识
DOI:10.1109/icassp55912.2026.11462388
摘要
Deep learning-based methods have achieved remarkable performance for image super-resolution in recent years. However, the majority of these approaches are not practical yet for real-world applications due to their excessive computational complexity and heavy memory consumption. In this work, we propose a lightweight image super-resolution network, Efficient Shift Convolution and Edge-enhanced Attention (ESCEA), where the Efficient Shift Convolution (ESC) is a method to simulate a larger convolutional kernel by shifting smaller ones, and therefore improves the SR performance by expanding the receptive field without increasing the computational complexity. The Edge-Enhanced Attention Block (EAB) is designed to enhance the learning ability of models for high-frequency components by integrating proposed Edge-Enhanced Convolution (EEC) into spatial attention module. Extensive experiments conducted across multiple benchmark datasets demonstrate that our proposed ESCEA demonstrates comparable performance in terms of PSNR and SSIM compared to state-of-the-art lightweight SR models, achieving an optimal trade-off between model performance and efficiency.
科研通智能强力驱动
Strongly Powered by AbleSci AI