Deformable Gaussian Splatting for Efficient and High-Fidelity Reconstruction of Surgical Scenes

TL;DR

This paper introduces EH-SurGS, a novel method for reconstructing deformable surgical scenes that effectively models irreversible tissue deformations and employs a hierarchical approach to improve rendering speed and quality.

Contribution

The paper presents a deformation modeling approach capturing irreversible changes and an adaptive hierarchy for faster rendering in surgical scene reconstruction.

Findings

Outperforms state-of-the-art in reconstruction quality

Achieves faster rendering speeds

Effectively models irreversible tissue deformations

Abstract

Efficient and high-fidelity reconstruction of deformable surgical scenes is a critical yet challenging task. Building on recent advancements in 3D Gaussian splatting, current methods have seen significant improvements in both reconstruction quality and rendering speed. However, two major limitations remain: (1) difficulty in handling irreversible dynamic changes, such as tissue shearing, which are common in surgical scenes; and (2) the lack of hierarchical modeling for surgical scene deformation, which reduces rendering speed. To address these challenges, we introduce EH-SurGS, an efficient and high-fidelity reconstruction algorithm for deformable surgical scenes. We propose a deformation modeling approach that incorporates the life cycle of 3D Gaussians, effectively capturing both regular and irreversible deformations, thus enhancing reconstruction quality. Additionally, we present an adaptive motion hierarchy strategy that distinguishes between static and deformable regions within the surgical scene. This strategy reduces the number of 3D Gaussians passing through the deformation field, thereby improving rendering speed. Extensive experiments demonstrate that our method surpasses existing state-of-the-art approaches in both reconstruction quality and rendering speed. Ablation studies further validate the effectiveness and necessity of our proposed components. We will open-source our code upon acceptance of the paper.