形状引导的高斯溅射用于稀疏视角X射线三维重建
Shape-guided Gaussian Splatting for Sparse-View X-ray 3D Reconstruction
- Polytechnique Montréal（蒙特利尔综合理工学院）
- Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）
- CHUM - University of Montreal Hospital（蒙特利尔大学医院中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出形状引导的高斯溅射框架，利用统计形状模型约束高斯位置和密度正则化，在仅5个稀疏视角下实现解剖一致的重建，PSNR提升2.83 dB。
AI中文摘要：
稀疏视角X射线三维重建对于减少辐射暴露至关重要，但从少量X射线投影中恢复密度场是严重不适定的问题。近年来，3D高斯溅射通过使用显式、优化的基元来表示体积，在稀疏视角重建中取得了最先进的性能，但它需要数十个投影视角。在更少的视角下，重建质量严重下降，因为显式基元在没有解剖信息的情况下自由优化。相比之下，解剖结构在人群中具有相似的几何形状和密度。它们的变异被限制在统计形状模型可以捕获的有限范围内。本文提出了一种形状引导的高斯溅射框架，用于稀疏视角X射线三维重建。我们的贡献在于将高斯位置驱动到解剖学上有效的配置，并结合基于图谱的密度正则化。我们的方法确保了解剖学上一致的重建，并且在仅5个视角下，相比最先进的高斯溅射基线，PSNR提高了2.83 dB。代码可用：此https URL
英文摘要：
Sparse-view X-ray 3D reconstruction is essential for reducing radiation exposure, but recovering a density field from a handful of X-ray projections is severely ill-posed. Recently, 3D Gaussian Splatting has achieved state-of-the-art performance in sparse-view reconstruction by representing the volume using explicit, optimized primitives, but it requires dozens of projected views. With fewer views, reconstruction quality degrades severely since the explicit primitives are optimized freely without any anatomical information. Anatomical structures, in contrast, share similar geometry and density across a population. Their variations are bounded within a limited range that statistical shape models can capture. This paper proposes a shape-guided Gaussian splatting framework for sparse-view X-ray 3D reconstructions. Our contribution lies in driving Gaussian positions toward anatomically valid configurations, alongside atlas-based density regularization. Our method ensures anatomically consistent reconstruction and improves PSNR by 2.83 dB over a state-of-the-art Gaussian splatting baseline with as few as 5 views. Code Available: https://github.com/polyshape-lab/ShapeGuidedGaussian
