Real-Time Spatio-Temporal Reconstruction of Dynamic Endoscopic Scenes with 4D Gaussian Splatting

TL;DR

This paper introduces ST-Endo4DGS, a real-time framework for reconstructing dynamic endoscopic scenes using 4D Gaussian Splatting, capturing tissue deformation and appearance changes with high fidelity.

Contribution

The paper presents a novel 4D Gaussian Splatting method for real-time, accurate reconstruction of dynamic endoscopic scenes, including new modeling, appearance representation, and geometric constraints.

Findings

Outperforms existing methods in visual quality

Achieves real-time reconstruction performance

Provides detailed modeling of tissue dynamics

Abstract

Dynamic scene reconstruction is essential in robotic minimally invasive surgery, providing crucial spatial information that enhances surgical precision and outcomes. However, existing methods struggle to address the complex, temporally dynamic nature of endoscopic scenes. This paper presents ST-Endo4DGS, a novel framework that models the spatio-temporal volume of dynamic endoscopic scenes using unbiased 4D Gaussian Splatting (4DGS) primitives, parameterized by anisotropic ellipses with flexible 4D rotations. This approach enables precise representation of deformable tissue dynamics, capturing intricate spatial and temporal correlations in real time. Additionally, we extend spherindrical harmonics to represent time-evolving appearance, achieving realistic adaptations to lighting and view changes. A new endoscopic normal alignment constraint (ENAC) further enhances geometric fidelity by aligning rendered normals with depth-derived geometry. Extensive evaluations show that ST-Endo4DGS outperforms existing methods in both visual quality and real-time performance, establishing a new state-of-the-art in dynamic scene reconstruction for endoscopic surgery.