Abstract. 3D Gaussian splatting has shown promise for high-fidelity 3D modeling in cultural heritage documentation. However, applying 3DGS to cultural artifacts faces challenges, including image alignment errors in dynamic capture environments and background interference from scene-level reconstruction. We propose an optimized 3DGS framework tailored for artifact modeling, introducing two key innovations: (1) COLMAP-free for robust image alignment under non-static conditions, and (2) implementing targeted isolation to separate artifacts from extraneous backgrounds. Our approach enhances reconstruction quality, preserving intricate geometric details and critical textures for cultural artifacts. Comprehensive evaluations against traditional photogrammetry and standard 3DGS demonstrate superior performance in accuracy and visual fidelity. Through enhanced 3D Gaussian splatting, the proposed method achieves precise 3D documentation of cultural artifacts, enabling diverse digital applications.
Lee et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: