发表机构
School of Information Engineering, Nanchang University; School of Computer Science and Engineering, Southeast University（南昌大学信息工程学院; 东南大学计算机科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对稀疏视图光谱CT重建的角欠采样与光谱耦合问题，提出共享结构4D光谱高斯表示（4D-SG）方法，在多类数据集上实验显示其相比基线方法提升了重建性能。
AI 中文摘要
稀疏视图光谱计算机断层扫描（CT）从有限的投影视图中重建能量分辨的衰减体积，需要同时处理角欠采样和光谱耦合问题。我们提出了一种共享结构4D光谱高斯表示（4D-SG），该表示从全谱结构投影中学习共享的高斯几何，并使用逐高斯光谱密度曲线网络（GSC-Net）预测高斯原始密度变换。这种分解将共享空间结构与光谱衰减变化分离开来，避免了独立通道几何优化，并从离散光谱测量中建立了用于未观测光谱通道查询的连续4D-SG表示。在包含50个视图的6个合成、模拟投影和真实投影数据集上进行的实验表明，该方法取得了最佳的平均性能。与最强的高斯基线相比，4D-SG将峰值信噪比（PSNR）从35.56 dB提升至36.61 dB，结构相似性指数（SSIM）从0.909提升至0.914，学习感知图像块相似性（LPIPS）从0.208降低至0.194，证明了其在稀疏视图光谱CT重建中的有效性。
英文摘要
Sparse-view spectral computed tomography (CT) reconstructs energy-resolved attenuation volumes from limited projection views, requiring simultaneous handling of angular undersampling and spectral coupling. We propose a SharedStructure 4D Spectral Gaussian Representation (4D-SG) that learns shared Gaussian geometry from full spectrum structural projections and uses a Gaussian-wise Spectral Density Curve Network (GSC-Net) to predict Gaussian raw density transformations. This factorization separates shared spatial structure from spectral attenuation variation, avoids independent channel geometry optimization, and establishes a continuous 4D-SG representation from discrete spectral measurements for unobserved spectral channel queries. Experiments on six synthesized, simulated projection, and real projection datasets with 50 views demonstrate the best average performance. Compared with the strongest Gaussian baseline, 4D-SG improves PSNR from 35.56 dB to 36.61 dB, increases SSIM from 0.909 to 0.914, and reduces LPIPS from 0.208 to 0.194, demonstrating its effectiveness for sparse-view spectral CT reconstruction.
