标题： 基于上采样的二维X射线投影先验的3D高斯点云零样本体积CT超分辨率 显示英文标题

标题： Zero-shot Volumetric CT Super-Resolution using 3D Gaussian Splatting with Upsampled 2D X-ray Projection Priors

摘要： 计算机断层扫描（CT）在临床诊断中被广泛应用，但获取高分辨率（HR）CT受到辐射暴露风险的限制。基于深度学习的超分辨率（SR）方法已被研究用于从低分辨率（LR）输入重建HR。虽然监督SR方法已显示出有希望的结果，但它们需要大规模的配对LR-HR体积数据集，这些数据集通常不可用。相反，零样本方法通过仅使用一个LR输入来减轻对配对数据的需求，但由于内部信息有限，通常难以恢复精细的解剖细节。为克服这些问题，我们提出了一种新颖的零样本3D CT SR框架，该框架利用由扩散模型生成的上采样的2D X射线投影先验。利用HR 2D X射线数据的丰富性，我们在大规模2D X射线投影上训练一个扩散模型，并引入一种每投影自适应采样策略。它为每个投影选择生成过程，从而提供HR投影作为3D CT重建的强外部先验。这些投影作为输入用于3D高斯点云重建3D CT体积。此外，我们提出了负alpha混合（NAB-GS），允许高斯密度表示中的负值。NAB-GS实现了LR与基于扩散的投影之间的残差学习，从而增强了高频结构的重建。在两个数据集上的实验表明，我们的方法在3D CT SR方面取得了优越的定量和定性结果。 显示英文摘要

摘要： Computed tomography (CT) is widely used in clinical diagnosis, but acquiring high-resolution (HR) CT is limited by radiation exposure risks. Deep learning-based super-resolution (SR) methods have been studied to reconstruct HR from low-resolution (LR) inputs. While supervised SR approaches have shown promising results, they require large-scale paired LR-HR volume datasets that are often unavailable. In contrast, zero-shot methods alleviate the need for paired data by using only a single LR input, but typically struggle to recover fine anatomical details due to limited internal information. To overcome these, we propose a novel zero-shot 3D CT SR framework that leverages upsampled 2D X-ray projection priors generated by a diffusion model. Exploiting the abundance of HR 2D X-ray data, we train a diffusion model on large-scale 2D X-ray projection and introduce a per-projection adaptive sampling strategy. It selects the generative process for each projection, thus providing HR projections as strong external priors for 3D CT reconstruction. These projections serve as inputs to 3D Gaussian splatting for reconstructing a 3D CT volume. Furthermore, we propose negative alpha blending (NAB-GS) that allows negative values in Gaussian density representation. NAB-GS enables residual learning between LR and diffusion-based projections, thereby enhancing high-frequency structure reconstruction. Experiments on two datasets show that our method achieves superior quantitative and qualitative results for 3D CT SR.