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

TL;DR

This survey comprehensively reviews computational methods for reconstructing complete objects from fractured parts, covering algorithms, datasets, software, and applications, highlighting the evolution from traditional to deep learning approaches.

Contribution

It is the first extensive survey in computer graphics that systematically compares existing algorithms, datasets, and trends in object reassembly from parts.

Findings

Deep learning approaches are increasingly replacing traditional methods.

Multiple datasets and open-source tools support research in object reconstruction.

Recent methods achieve higher accuracy in shape matching and segmentation.

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.