用四维高斯表示法，提升低视角光谱CT重建质量
Shared-Structure 4D Spectral Gaussian Representation for Sparse-View Spectral CT Reconstruction
- 将空间结构与光谱变化解耦，用高斯密度网络预测光谱响应
- 在50视角下，PSNR提升至36.61dB，SSIM达0.914
- 适合做光谱CT重建的科研人员和医学影像工程师
稀疏视角光谱计算机断层扫描（CT）需从有限投影视图中重建能量分辨衰减体积，同时应对角度欠采样与光谱耦合问题。本文提出共享结构四维光谱高斯表示（4D-SG），从全谱结构投影中学习共享高斯几何，并通过高斯级光谱密度曲线网络（GSC-Net）预测高斯原始密度变换。该方法将共享空间结构与光谱衰减变化分离，避免各通道独立几何优化，从离散光谱测量建立连续4D-SG表示，支持未观测光谱通道查询。在六个合成、模拟及真实投影数据集上，使用50个视角的实验表明，4D-SG性能最优。相比最强高斯基线，其PSNR由35.56 dB提升至36.61 dB，SSIM由0.909增至0.914，LPIPS由0.208降至0.194，验证了其在稀疏视角光谱CT重建中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。