English

LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT

Computer Vision and Pattern Recognition 2025-08-07 v2 Machine Learning Numerical Analysis Numerical Analysis

Abstract

Inverse problems arise in many applications, especially tomographic imaging. We develop a Learned Alternating Minimization Algorithm (LAMA) to solve such problems via two-block optimization by synergizing data-driven and classical techniques with proven convergence. LAMA is naturally induced by a variational model with learnable regularizers in both data and image domains, parameterized as composite functions of neural networks trained with domain-specific data. We allow these regularizers to be nonconvex and nonsmooth to extract features from data effectively. We minimize the overall objective function using Nesterov's smoothing technique and residual learning architecture. It is demonstrated that LAMA reduces network complexity, improves memory efficiency, and enhances reconstruction accuracy, stability, and interpretability. Extensive experiments show that LAMA significantly outperforms state-of-the-art methods on popular benchmark datasets for Computed Tomography.

Keywords

Cite

@article{arxiv.2410.21111,
  title  = {LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT},
  author = {Chi Ding and Qingchao Zhang and Ge Wang and Xiaojing Ye and Yunmei Chen},
  journal= {arXiv preprint arXiv:2410.21111},
  year   = {2025}
}

Comments

arXiv:2507.22316 is intended to replace this paper

R2 v1 2026-06-28T19:38:10.170Z