TE-SAGAN: An Improved Generative Adversarial Network for Remote Sensing Super-Resolution Images

• Published in: Remote sensing (Basel, Switzerland) Vol. 14; no. 10; p. 2425
• Main Authors: Xu, Yongyang, Luo, Wei, Hu, Anna, Xie, Zhong, Xie, Xuejing, Tao, Liufeng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.05.2022
• Subjects: Algorithms; Datasets; Deep learning; Feature extraction; generative adversarial network; Generative adversarial networks; Image enhancement; Image quality; Image reconstruction; Image resolution; joint loss; Land use; Machine learning; Methods; Neural networks; Remote sensing; self-attention mechanism; Semantics; super-resolution image; Texture; Training; weight normalization

Resolution is a comprehensive reflection and evaluation index for the visual quality of remote sensing images. Super-resolution processing has been widely applied for extracting information from remote sensing images. Recently, deep learning methods have found increasing application in the super-res...