A Progressive Gaussian Splatting Framework for Monocular-Only High-Fidelity Surgical Scene Reconstruction
IEEE Transactions on Biomedical Engineering · 2026-08 · 73 (8) · 2911-2921
DOI: 10.1109/tbme.2026.3701768 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2026-08. Verfasst von Yuchao Zheng und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Surgery, Computer-Assisted, Minimally Invasive Surgical Procedures. Die Arbeit nennt 45 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Accurate and reliable 3D scene reconstruction is a key component of intelligent surgery, enabling enhanced spatial understanding and data-driven analysis in minimally invasive surgery (MIS). However, existing clinical systems are often bulky and workflow-incompatible, while vision-based Structure-from-Motion methods struggle with sparse textures and specularities, leading to unstable pose estimation and high computational cost. To address these limitations, we present SurGSplat++, a progressive, pose-free Gaussian splatting framework for monocular surgical scene reconstruction that requires no auxiliary hardware or pre-computed camera poses. Experiments show that SurGSplat++ achieves improved geometric stability, reduced pose drift, and superior novel-view synthesis compared with existing approaches. By producing accurate and consistent 3D reconstructions, the proposed method provides a practical solution for post-operative analysis, pre-operative planning, and data-driven surgical modeling in clinical environments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Zitieren
APA
Zheng, Y., Zhang, J., Wu, Y., Liao, H., & Ning, G. (2026). A Progressive Gaussian Splatting Framework for Monocular-Only High-Fidelity Surgical Scene Reconstruction. IEEE Transactions on Biomedical Engineering, 73(8), 2911-2921. https://doi.org/10.1109/tbme.2026.3701768
Vancouver
Zheng Y, Zhang J, Wu Y, Liao H, Ning G. A Progressive Gaussian Splatting Framework for Monocular-Only High-Fidelity Surgical Scene Reconstruction. IEEE Transactions on Biomedical Engineering. 2026;73(8):2911-2921. doi:10.1109/tbme.2026.3701768
BibTeX
@article{Zheng2026,
author = {Zheng, Yuchao and Zhang, Jianing and Wu, Yutong and Liao, Hongen and Ning, Guochen},
title = {A Progressive Gaussian Splatting Framework for Monocular-Only High-Fidelity Surgical Scene Reconstruction},
journal = {IEEE Transactions on Biomedical Engineering},
year = {2026},
volume = {73},
number = {8},
pages = {2911--2921},
doi = {10.1109/tbme.2026.3701768}
}
EUVIMED