BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fehrentz, Maximilian, Winkler, Alexander, Heiliger, Thomas, Haouchine, Nazim, Heiliger, Christian, Navab, Nassir
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911171322314752
author Fehrentz, Maximilian
Winkler, Alexander
Heiliger, Thomas
Haouchine, Nazim
Heiliger, Christian
Navab, Nassir
author_facet Fehrentz, Maximilian
Winkler, Alexander
Heiliger, Thomas
Haouchine, Nazim
Heiliger, Christian
Navab, Nassir
contents 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/ .
format Preprint
id arxiv_https___arxiv_org_abs_2509_18501
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation
Fehrentz, Maximilian
Winkler, Alexander
Heiliger, Thomas
Haouchine, Nazim
Heiliger, Christian
Navab, Nassir
Computer Vision and Pattern Recognition
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/ .
title BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.18501