PhyDiff: Physics-guided latent diffusion model for sparse-view CT projection interpolation.
Authors
Affiliations (8)
Affiliations (8)
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China. Electronic address: [email protected].
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China; Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, 200444, China; Key Laboratory of Silicate Cultural Relics Conservation, Ministry of Education, Shanghai University, Shanghai, 200444, China; Wuxi Zhongdun Technology Co., Ltd, Wuxi, 214000, China; Materials Genome Institute, Shanghai University, Shanghai, 200444, China. Electronic address: [email protected].
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China. Electronic address: [email protected].
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China. Electronic address: [email protected].
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China. Electronic address: [email protected].
- School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China; Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, 200444, China; Key Laboratory of Silicate Cultural Relics Conservation, Ministry of Education, Shanghai University, Shanghai, 200444, China; Materials Genome Institute, Shanghai University, Shanghai, 200444, China. Electronic address: [email protected].
- Department of Geography, Hong Kong Baptist University, Hong Kong, 999077, China. Electronic address: [email protected].
- Institute for Data Engineering and Science, University of Saint Joseph, Macao, 999078, China. Electronic address: [email protected].
Abstract
Sparse-view Computed Tomography (SVCT) is an important strategy for minimizing radiation exposure and accelerating industrial inspection, yet it suffers from severe streak artifacts under angular undersampling. Existing sinogram completion methods often process detector rows independently, failing to exploit cross-row correlations to maintain the structural consistency required for high-fidelity reconstruction. To address this, we propose PhyDiff, a physics-guided latent diffusion framework that reformulates sparse-view projection completion as an angle-conditioned sequence interpolation. PhyDiff incorporates the known acquisition angles to condition cross-view alignment and exploit geometric correlations between adjacent projections. Specifically, a Physical-Geometric Autoencoder (PGAE) decomposes projection synthesis into geometry-guided warping and residual refinement. The warping model captures the dominant translation and scale variation between neighboring views, while the residual branch recovers spatially varying residuals that cannot be represented by the low-order transformation. Furthermore, a Spectral-Aware Latent Diffusion (SALD) model introduces angle-conditioned spectral modulation into the generative process to preserve fine structural details. Experimental results on simulated and measured datasets demonstrate that PhyDiff consistently improves projection fidelity under different acquisition geometries.