Rejoining fragmented ancient bamboo slips with physics-driven deep learning

2025-05-13

AI Summary

Automatic reassembly of archaeological bamboo-strip fragments faces severe challenges due to scarcity of ground-truth annotations and low matching accuracy. Method: This paper proposes WisePanda, a physics-driven deep learning framework that uniquely integrates bamboo fracture mechanics and aging degradation models into both generative data synthesis and an end-to-end contour matching network, enabling training without paired samples. By embedding domain-specific physical priors, it overcomes reliance on supervised labels and establishes a novel paradigm for cultural heritage restoration. Contribution/Results: Experiments demonstrate that WisePanda improves Top-50 matching accuracy from 36% to 52%, accelerating archaeologists’ manual assembly efficiency by approximately 20×. This work introduces a generalizable physics–data co-design paradigm for intelligent reconstruction of fragile organic artifacts.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data integration and cleaning
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Bamboo slips are a crucial medium for recording ancient civilizations in East Asia, and offers invaluable archaeological insights for reconstructing the Silk Road, studying material culture exchanges, and global history. However, many excavated bamboo slips have been fragmented into thousands of irregular pieces, making their rejoining a vital yet challenging step for understanding their content. Here we introduce WisePanda, a physics-driven deep learning framework designed to rejoin fragmented bamboo slips. Based on the physics of fracture and material deterioration, WisePanda automatically generates synthetic training data that captures the physical properties of bamboo fragmentations. This approach enables the training of a matching network without requiring manually paired samples, providing ranked suggestions to facilitate the rejoining process. Compared to the leading curve matching method, WisePanda increases Top-50 matching accuracy from 36% to 52%. Archaeologists using WisePanda have experienced substantial efficiency improvements (approximately 20 times faster) when rejoining fragmented bamboo slips. This research demonstrates that incorporating physical principles into deep learning models can significantly enhance their performance, transforming how archaeologists restore and study fragmented artifacts. WisePanda provides a new paradigm for addressing data scarcity in ancient artifact restoration through physics-driven machine learning.

Problem

• Rejoining fragmented ancient bamboo slips using deep learning
• Overcoming data scarcity in artifact restoration with physics-driven ML
• Improving accuracy and efficiency in archaeological fragment matching

Innovation

• Physics-driven deep learning for bamboo slip rejoining
• Synthetic training data from fracture physics
• Automated ranked suggestions without manual samples