MultiRegNet: A Novel Multimodal Registration Network Framework for the 3-D CT-Volume and 3-D Point Cloud Data

Cultural heritage preservation benefits greatly from integrating multimodal data, such as point clouds and 3-D computed tomography (3DCT), for artifact analysis, damage detection, and digital preservation. However, aligning these datasets accurately remains challenging due to their differing structures and levels of detail. To address this, we introduce MultiRegNet, an advanced deep learning (DL) framework designed to align point clouds and 3DCT data precisely. The framework introduces a universal 3-D multihead self-attention module and an adapted bidirectional cross-attention module to improve feature representation in both data types. The 3-D multihead self-attention module enhances local and global feature representations by integrating spatial geometry and context. It introduces dynamic positional encoding, embedding 3-D spatial relationships into attention computation. This enables precise capturing of local details and strengthens global structural perception, improving the module’s ability to represent geometric and structural data characteristics effectively. The adapted bidirectional cross-attention module fosters feature interaction between modalities, identifying correspondences between point clouds and 3DCT surface voxels. Testing on datasets (3DPCD-CT, WoodCarving, and Jade Tower) shows that MultiRegNet surpasses traditional and existing DL methods in accuracy and robustness. By aligning point clouds and 3DCT, it enables precise digital representations of cultural artifacts, advancing their preservation and analysis. This framework can provide precise digital representation and actionable insights for cultural heritage preservation.