3 papers
math.NA2026
Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators
Xiang Cao, Qiaoqiao Ding, Xinliang Liu +2
Ultrasound Computed Tomography (USCT) constitutes a nonlinear inverse problem with inherent ill-posedness that can benefit from regularization through diffusion generative priors.…
math.NA2025
Multi-Scale Frequency-Enhanced Deep D-bar Method for Electrical Impedance Tomography
Xiang Cao, Qiaoqiao Ding, Xiaoqun Zhang
The regularized D-bar method is a popular method for solving Electrical Impedance Tomography (EIT) problems due to its efficiency and simplicity. It utilizes the low-pass truncated…
math.NA2024
Subspace Diffusion Posterior Sampling for Travel-Time Tomography
Xiang Cao, Xiaoqun Zhang
Diffusion models have been widely studied as effective generative tools for solving inverse problems. The main ideas focus on performing the reverse sampling process conditioned on…