arXiv 2410.092922024-10-11cs.CV

SurgicalGS：用于精确机器人辅助手术场景重建的动态3D高斯泼溅

SurgicalGS: Dynamic 3D Gaussian Splatting for Accurate Robotic-Assisted Surgical Scene Reconstruction

The Hamlyn Centre for Robotic Surgery, Imperial College London（伦敦帝国理工学院哈姆林 robotic外科中心）；Hawkes Institute, University College London（伦敦大学学院霍克斯研究所）；University of Liverpool（利物浦大学）

Jialei Chen, Xin Zhang, Mobarakol Islam, Francisco Vasconcelos, Danail Stoyanov, Daniel S. Elson, Baoru Huang

备注：: 7 pages

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出SurgicalGS动态3D高斯泼溅框架，通过深度先验初始化、Flexible Deformation Model及深度正则化约束，提升机器人辅助手术场景的3D重建几何精度，在两个真实数据集上达到最先进水平。

摘要：

从内窥镜视频中对动态手术场景进行精确的3D重建对于机器人辅助手术至关重要。尽管最近的3D高斯泼溅方法在实现高质量重建和快速渲染速度方面展现出潜力，但其使用的逆深度损失函数压缩了深度变化。这可能导致精细几何细节的丢失，限制了其捕捉精确3D几何的能力及在术中应用中的有效性。为了解决这些挑战，我们提出了SurgicalGS，这是一个专为手术场景重建设计的动态3D高斯泼溅框架，具有更高的几何精度。该方法首先使用深度先验初始化高斯点云，采用二值运动掩码识别具有显著深度变化的像素，并融合跨帧深度图中的点云进行初始化。我们使用Flexible Deformation Model表示动态场景，并引入归一化深度正则化损失和无监督深度平滑约束，以确保更精确的几何重建。在两个真实手术数据集上的大量实验表明，SurgicalGS实现了最先进的重建质量，尤其是在精确几何方面，推动了3D高斯泼溅在机器人辅助手术中的可用性。

英文摘要：

Accurate 3D reconstruction of dynamic surgical scenes from endoscopic video is essential for robotic-assisted surgery. While recent 3D Gaussian Splatting methods have shown promise in achieving high-quality reconstructions with fast rendering speeds, their use of inverse depth loss functions compresses depth variations. This can lead to a loss of fine geometric details, limiting their ability to capture precise 3D geometry and effectiveness in intraoperative application. To address these challenges, we present SurgicalGS, a dynamic 3D Gaussian Splatting framework specifically designed for surgical scene reconstruction with improved geometric accuracy. Our approach first initialises a Gaussian point cloud using depth priors, employing binary motion masks to identify pixels with significant depth variations and fusing point clouds from depth maps across frames for initialisation. We use the Flexible Deformation Model to represent dynamic scene and introduce a normalised depth regularisation loss along with an unsupervised depth smoothness constraint to ensure more accurate geometric reconstruction. Extensive experiments on two real surgical datasets demonstrate that SurgicalGS achieves state-of-the-art reconstruction quality, especially in terms of accurate geometry, advancing the usability of 3D Gaussian Splatting in robotic-assisted surgery.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。