.png){kind=icon}
.png){kind=icon}
Return
A diffusion-based generative prior approach to sparse-view computed tomography
.png){kind=icon}
OA
AI
D
P
E
DOI：10.1016/j.compmedimag.2026.102802.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Diffusion models are used as generative priors for sparse-view CT reconstruction. • A Regularized Deep Generative Prior framework is formulated via latent optimization. • Physics-informed initialization via FBP and DDIM inversion improves convergence. • Cosine-annealed optimization improves reconstruction performance. • Competitive performance is achieved under extremely sparse acquisition geometries.
Keywords:
Deep Generative Prior
Diffusion models
Regularization
Model-based reconstruction
Sparse tomography
Journal
IF:
4.9
Papers:
2.4K
Citations:
5.0K
Organization
Cited Papers