IEEE

Light-SLAM: A Robust Deep-Learning Visual SLAM System Based on LightGlue Under Challenging Lighting Conditions

Abstract: Simultaneous Localization and Mapping (SLAM) has become a critical technology for intelligent transportation systems and autonomous robots and is widely used in autonomous driving. However, ...
IEEE

Deep Learning in Remote Sensing Image Fusion: Methods, protocols, data, and future perspectives

Abstract: Image fusion can be conducted at different levels, with pixel-level image fusion involving the direct combination of original information from source images. The objective of methods falling ...
The Lancet

Development of a multi-task deep learning system for classification of nine common knee abnormalities on MRI: a large-scale, multicentre, stepwise validation study

aDepartment of Radiology, The Third Affiliated Hospital of Southern Medical University, Guangzhou, China bInstitute of High-End Intelligent Health Equipment, Academy of Orthopedics, Guangdong Province ...
PNAS

Accurate prediction of discontinuous crack paths in random porous media via a generative deep learning model

Porous media are susceptible to fracture. A deep understanding of crack propagation in porous microstructures remains limited to date, owing to the unacceptably expensive cost of numerical modeling ...