ELDGG: an end-to-end LiDAR-dynamic-guided GAN for hyperspectral image hierarchical reconstruction and classification

Xingyue Zhang, Mingju Chen, Senyuan Li, Xiao Hu, Zhengxu Duan, Yangming Luo, Chen Xie, Xingzhong Xiong · 2025

Read ELDGG: an end-to-end LiDAR-dynamic-guided GAN for hyperspectral image hierarchical reconstruction and classification by Xingyue Zhang, Mingju Chen, Senyuan Li, Xiao Hu, Zhengxu Duan, Yangming Luo, Chen Xie, Xingzhong Xiong (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12789626.txt.

Description

Zhang and seven co-authors fused satellite data types with a GAN in this paper from twenty twenty-five. Hyperspectral images carry rich color detail but blurry space detail, while LiDAR gives precise heights. The authors' network lets the LiDAR data steer the fusion dynamically. A generator rebuilds features layer by layer under that guidance.

An implicit field unit maps coordinates to features for crisp, artifact-free detail. The discriminator judges realism at three scales, from texture to meaning, with spectral rules added. A final classifier reads the fused maps into land cover labels. Tests showed gains in both fusion quality and classification accuracy. The design targets adaptive interaction between the two data types.

Catalog record

CREATORXingyue Zhang, Mingju Chen, Senyuan Li, Xiao Hu, Zhengxu Duan, Yangming Luo, Chen Xie, Xingzhong Xiong
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE84 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12789626

Browse the full library · About the Tower of Babel