BridgeSplat：用于可变形术中手术导航的双向耦合CT与非刚性高斯泼溅
BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation
AI总结：
BridgeSplat通过将三维高斯绑定到术前CT网格并联合优化高斯参数与网格变形，实现术中单目RGB视频驱动的可变形手术导航，并在猪内脏手术和模拟人类肝脏数据上验证了术前CT的合理变形更新。
摘要：
我们提出BridgeSplat，这是一种用于可变形手术导航的新方法，它将术中三维重建与术前CT数据耦合，以弥合手术视频与体积患者数据之间的差距。我们的方法将三维高斯绑定到CT网格上，通过光度监督实现高斯参数与网格变形的联合优化。通过将每个高斯参数化到其父网格三角形上，我们强制高斯与网格之间的对齐，并获得可传播回以更新CT的变形。我们在猪内脏手术和模拟条件下人类肝脏的合成数据上展示了BridgeSplat的有效性，表明在单目RGB数据上术前CT发生了合理的变形。代码、数据和额外资源可在https://maxfehrentz.github.io/ct-informed-splatting/找到。
英文摘要：
We introduce BridgeSplat, a novel approach for deformable surgical navigation that couples intraoperative 3D reconstruction with preoperative CT data to bridge the gap between surgical video and volumetric patient data. Our method rigs 3D Gaussians to a CT mesh, enabling joint optimization of Gaussian parameters and mesh deformation through photometric supervision. By parametrizing each Gaussian relative to its parent mesh triangle, we enforce alignment between Gaussians and mesh and obtain deformations that can be propagated back to update the CT. We demonstrate BridgeSplat's effectiveness on visceral pig surgeries and synthetic data of a human liver under simulation, showing sensible deformations of the preoperative CT on monocular RGB data. Code, data, and additional resources can be found at https://maxfehrentz.github.io/ct-informed-splatting/ .
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。
