A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts

2024-10-18

arXiv.org

AI Summary

This paper presents a systematic survey of the 3D fragment reassembly problem: reconstructing an intact object from a set of discrete, possibly damaged or incomplete fragments. Methodologically, it unifies three core components—shape segmentation, inter-fragment correspondence matching, and object prior modeling—covering classical geometric approaches as well as modern deep learning paradigms, including point-cloud networks and graph neural networks, while integrating state-of-the-art feature extraction techniques, probabilistic modeling strategies, and open-source toolchains. Its primary contribution is the first comprehensive, panoramic survey of this problem in computer graphics, establishing a precise formal definition, delineating problem boundaries, and proposing a unified taxonomy spanning algorithms, benchmark datasets, and software resources. The survey serves as a reusable methodological guide and practical benchmark for applications such as archaeological restoration, medical image reconstruction, and intelligent manufacturing, thereby fostering cross-disciplinary methodological synergy.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Reconstructing a complete object from its parts is a fundamental problem in many scientific domains. The purpose of this article is to provide a systematic survey on this topic. The reassembly problem requires understanding the attributes of individual pieces and establishing matches between different pieces. Many approaches also model priors of the underlying complete object. Existing approaches are tightly connected problems of shape segmentation, shape matching, and learning shape priors. We provide existing algorithms in this context and emphasize their similarities and differences to general-purpose approaches. We also survey the trends from early non-deep learning approaches to more recent deep learning approaches. In addition to algorithms, this survey will also describe existing datasets, open-source software packages, and applications. To the best of our knowledge, this is the first comprehensive survey on this topic in computer graphics.

Problem

• Survey computational solutions for reassembling fractured object parts
• Compare algorithms for shape segmentation and matching in reconstruction
• Review trends from non-deep to deep learning approaches

Innovation

• Survey computational solutions for fractured object reassembly
• Compare shape segmentation and matching algorithms
• Review deep learning versus traditional approaches