English(EN) LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction

LUCID框架使用流匹配进行稀疏视图CT重建

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-16 04:00

研究人员推出了一种新颖的LUCID框架，用于从稀疏视图数据中重建高质量的计算机断层扫描（CT）图像。该方法利用流匹配进行生成建模，使其能够适应不同程度的欠采样，而无需为每种设置进行特定训练。LUCID学习高斯分布与高质量CT图像之间的连续传输，并在推理过程中，它会纳入稀疏度级别来调节生成过程，提高图像质量和结构保真度，同时降低出现幻影结构的风险。 AI

排序理由该集群包含一篇详细介绍新图像重建方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Jigang Duan, Jiayi Wang, Heran Wang, Ping Yang, Genwei Ma, Xing Zhao · 2026-06-16 04:00

LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction

arXiv:2606.16212v1 Announce Type: cross Abstract: Sparse-view CT reduces radiation dose and scanning time by acquiring fewer projection views, but angular undersampling makes reconstruction severely ill-posed, causing streak artifacts, structural blurring, and loss of fine detail…

报道来源 [1]

LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction

相关实体

相关话题