A comparative study of variational autoencoders, normalizing flows, and score-based diffusion models for electrical impedance tomography

• Published in: Journal of inverse and ill-posed problems Vol. 32; no. 4; pp. 795 - 813
• Main Authors: Wang, Huihui, Xu, Guixian, Zhou, Qingping
• Format: Journal Article
• Language: English
• Published: Berlin De Gruyter 01.08.2024; Walter de Gruyter GmbH
• Subjects: 68U10; 78A46; Algorithms; Anomalies; Comparative studies; deep generative model; deep learning; Diffusion models; Electrical impedance; Electrical impedance tomography; Image reconstruction; Imaging techniques; Inverse problems; Learning; Medical imaging; Nonlinearity; Regularization; Tomography

Electrical Impedance Tomography (EIT) is a widely employed imaging technique in industrial inspection, geophysical prospecting, and medical imaging. However, the inherent nonlinearity and ill-posedness of EIT image reconstruction present challenges for classical regularization techniques, such as th...