Depth-Aware Gaussian Splatting with Dynamic Masking for High-Fidelity Geometric Modeling of Shield Tunnel Digital Twins

Abstract

The construction of high-fidelity twin geometric models is essential for advancing tunnel digital-twin technology. Image-based three-dimensional (3D) reconstruction, which directly infers 3D scene structures from visual semantics, has demonstrated considerable potential. However, most existing approaches rely on the conventional structure-from-motion (SfM) and multiview stereo (MVS) pipeline, which often suffers from point cloud voids and texture blurring in shield tunnel environments with low-texture segments and dim lighting. In addition, the inherent discreteness of point cloud representations makes subsequent denoising and optimization inefficient. To address these limitations, this study proposes a two-dimensional (2D) Gaussian splatting (2DGS) modeling approach integrated with a dynamic depth-aware masking mechanism. Image data are efficiently captured from a tunnel-longitudinal viewpoint, and sparse point clouds reconstructed via SfM are parameterized using 2DGS to enable adaptive geometric reconstruction under image supervision. Considering the linear and long-distance geometric characteristics of shield tunnels, a depth-aware dynamic masking strategy is introduced to guide the model to focus on near-field structural optimization under longitudinal viewing conditions. The optimized Gaussian model is rendered into depth maps at each camera viewpoint and fused using a truncated signed distance function to generate the final shield tunnel digital-twin geometric model. Experimental results from real tunnel engineering scenarios show that the proposed method achieves a geometric accuracy error of only 0.7% compared with SfM+MVS methods, significantly alleviates voids and local blurring artifacts, produces clearer segment contours, and reduces modeling time by approximately 37%. The proposed approach provides a novel technical paradigm for shield tunnel digital-twin geometric modeling.