用几何约束逐步优化3D高斯点云，提升手术场景重建精度
SurGSplat: Progressive Geometry-Constrained Gaussian Splatting for Surgical Scene Reconstruction
- 引入几何约束逐步优化3D高斯点云的重建过程
- 在新视角合成和位姿估计上均超越现有方法
- 适合需要高保真术中三维重建的外科医生
术中导航依赖精准的三维重建以保障手术准确与安全。然而，内窥镜场景存在特征稀疏、光照不一致等挑战，使许多基于结构光（SfM）的方法失效且易失败。为此，我们提出SurGSplat，一种通过集成几何约束逐步优化3D高斯点云（3DGS）的新范式。该方法能精确重建血管等关键结构，增强术中视觉清晰度，辅助医生精准决策。实验表明，SurGSplat在新视角合成（NVS）和位姿估计精度方面均表现优异，为手术场景重建提供了高保真、高效解决方案。更多信息与结果见https://surgsplat.github.io/。
原文摘要 · Abstract (English)
Intraoperative navigation relies heavily on precise 3D reconstruction to ensure accuracy and safety during surgical procedures. However, endoscopic scenarios present unique challenges, including sparse features and inconsistent lighting, which render many existing Structure-from-Motion (SfM)-based methods inadequate and prone to reconstruction failure. To mitigate these constraints, we propose SurGSplat, a novel paradigm designed to progressively refine 3D Gaussian Splatting (3DGS) through the integration of geometric constraints. By enabling the detailed reconstruction of vascular structures and other critical features, SurGSplat provides surgeons with enhanced visual clarity, facilitating precise intraoperative decision-making. Experimental evaluations demonstrate that SurGSplat achieves superior performance in both novel view synthesis (NVS) and pose estimation accuracy, establishing it as a high-fidelity and efficient solution for surgical scene reconstruction. More information and results can be found on the page https://surgsplat.github.io/.
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。