Researchers have introduced LUCID, a novel framework for reconstructing high-quality computed tomography (CT) images from sparse-view data. This method utilizes Flow Matching for generative modeling, enabling it to adapt to varying levels of undersampling without requiring specific training for each setting. LUCID learns a continuous transport between a Gaussian distribution and high-quality CT images, and during inference, it incorporates the sparsity level to modulate the generative process, improving image quality and structural fidelity while reducing the risk of hallucinated structures. AI
RANK_REASON The cluster contains an academic paper detailing a new method for image reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →