Monocular Endoscopic Tissue 3D Reconstruction with Multi-Level Geometry Regularization

TL;DR

This paper presents a novel 3D reconstruction method for deformable endoscopic tissues using 3D Gaussian Splatting, achieving real-time rendering and smooth surface reconstruction with physical plausibility.

Contribution

It introduces a surface-aware reconstruction framework with mesh constraints and deformation restrictions, enhancing real-time, high-quality tissue surface reconstruction.

Findings

Achieves fast rendering and smooth surface appearance.

Provides accurate texture and geometry reconstruction.

Outperforms existing methods in quality metrics.

Abstract

Reconstructing deformable endoscopic tissues is crucial for achieving robot-assisted surgery. However, 3D Gaussian Splatting-based approaches encounter challenges in achieving consistent tissue surface reconstruction, while existing NeRF-based methods lack real-time rendering capabilities. In pursuit of both smooth deformable surfaces and real-time rendering, we introduce a novel approach based on 3D Gaussian Splatting. Specifically, we introduce surface-aware reconstruction, initially employing a Sign Distance Field-based method to construct a mesh, subsequently utilizing this mesh to constrain the Gaussian Splatting reconstruction process. Furthermore, to ensure the generation of physically plausible deformations, we incorporate local rigidity and global non-rigidity restrictions to guide Gaussian deformation, tailored for the highly deformable nature of soft endoscopic tissue. Based on 3D Gaussian Splatting, our proposed method delivers a fast rendering process and smooth surface appearances. Quantitative and qualitative analysis against alternative methodologies shows that our approach achieves solid reconstruction quality in both textures and geometries.