Ganet: graph attention based Terracotta Warriors point cloud completion network

Abstract Point cloud completion technology is used to address incomplete three-dimensional point cloud data, predicting and reconstructing the original shape and details to achieve virtual restoration. While existing learning-based methods have made significant progress in point cloud completion, they still face challenges when dealing with noise and invisible data. To address these issues, this paper proposes a multi-layer upsampling network based on a graph attention mechanism, called GANet. GANet consists of three main components: (1) feature extraction; (2) seed point generation; (3) State Space Model-based Point Cloud Upsampling Layer. GANet demonstrates exceptional robustness in handling noise and invisible data. To validate the effectiveness of GANet, we applied it to Terracotta Warrior data. The Terracotta Warriors, as important cultural heritage, present a challenging test case due to damage and missing parts caused by prolonged burial and environmental factors. We trained and tested GANet on both the PCN dataset and Terracotta Warrior data, comparing it with several recent learning-based methods. Experimental results show that GANet can effectively reconstruct missing or damaged parts of 3D point clouds, providing more detailed and structurally accurate completion results. These completion models not only validate GANet’s effectiveness but also offer valuable references for cultural heritage restoration work.