Classification of 3D Terracotta Warrior Fragments Based on Deep Learning and Template Guidance

Abstract

The Terracotta Warriors are terracotta sculptures created for China's first emperor more than 2,000 years ago. They are among the most precious unearthed cultural relics of China. However, these relics have been predominantly found in fragments. Fragment classification is currently performed manually on enormous quantities of fragments, which is a time-consuming, inaccurate, and subjective task for archaeologists and conservators. In this study, an automatic method based on a deep learning network combined with template guidance is proposed to classify 3D fragments of the Terracotta Warriors. The fragments are initially classified using PointNet. Then, misclassified fragments are secondly categorized based on their best match to a complete Terracotta Warrior model. Extensive experiments were performed to verify the effectiveness of the proposed method. The promising results demonstrate that the method is the most accurate technique for classifying 3D Terracotta Warrior fragments to date. Moreover, the proposed method can significantly increase the efficiency of future fragment reassembly for the Terracotta Warriors. INDEX TERMS Data preprocessing, deep learning, 3D fragments classification, intrinsic shape signatures, point cloud, random sample consensus, signature of histograms of orientations, Terracotta warriors.

Research on Digital Restoration of Plain Unlined Silk Gauze Gown of Mawangdui Han Dynasty Tomb Based on AHP and Human–Computer Interaction Technology

“…Compared with traditional silk fabric protection technology [8,9], the color of the clothes produced by virtual simulation is more vivid and durable. Compared with the traditional digital restoration of rigid cultural relics [16][17][18][19][20][21][22][23][24][25], the research method combining reverse engineering and virtual simulation proposed in this paper provides a reference for the digital restoration of flexible cultural relics.…”

“…Hou et al proposed a novel method for the virtual restoration of cultural relics with a complex geometric structure based on multiscale spatial geometry [18]. Chu, Gao and Yang et al applied virtual reality and deep learning technologies to study the classification, restoration and restoration of the fragments of the Terracotta Warriors [19][20][21]. Chen et al proposed a method for modeling and supporting digital restoration based on unmanned aerial vehicle oblique photogrammetry combined with 3D laser scanning technology to restore the ancient watchtower complex in the Tibetan region of China [22].…”

AMS-Net: An Attention-Based Multi-Scale Network for Classification of 3D Terracotta Warrior Fragments

“…[31] image F 84.34 Method in [10] image F 86.86 Method in [19] image (cnn-based) T 89.54 Method in [32] pnt. F 87.64 PointNet [24] pnt., T 88.93 Method in [25] pnt., T 90.94 Method in [26] pnt Without normal, the classification accuracies of the four classes are 98.1% (Body), 98.0% (Head), 94.2% (Leg), and 92.4% (Arm). Figure 12 show some representative fragments of the four classes.…”

“…PointNet [24] directly takes point cloud as its input and achieves permutation invariance with a symmetric function as a pioneering work. Inspire by PointNet, Gao et al [25] present an automatic method combined with template guidance to classify 3D fragments of the Terracotta Warriors. In [26], the proposed method can directly consume the point cloud and texture image of the fragment and outputs its category.…”

SPPD: A Novel Reassembly Method for 3D Terracotta Warrior Fragments Based on Fracture Surface Information

“…They are known for their large numbers, vivid appearances, and diverse postures, and they are of great value in history, archaeology, art, and the tourist industry. However, owing to thousands of years of weathering erosion and earth crust movement, a large number of the Terracotta Warriors have been damaged and gathered in piles of fragments [1]. To restore the original appearance, the reassembly task is essential.…”