3D puzzle reconstruction for archeological fragments

Jampy, Florian; Hostein, Antony; Fauvet, Éric; Laligant, Olivier; Truchetet, Frédéric

doi:10.1117/12.2075655

Cited by 7 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As explained in section 3.1, we devised our model in order to work with an imbalanced DS (when undersampling was not used), therefore in order to show the effectiveness of the adopted technique we used two kinds of classification metrics: the balanced accuracy and the macro F1 score. The first one is defined as the average of recall obtained on each class 8 , while the second one calculates metrics for each label and finds their unweighted mean 9 . Thus, macro F1 is defined as follows:…”

Section: Experiments and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial neural networks exploiting point cloud data for fragmented solid objects classification

Baiocchi,

Giagu,

Napoli

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

This paper presents a novel approach for fragmented solid object classification exploiting neural networks based on point clouds. This work is the initial step of a project in collaboration with the Institution of ‘Ente Parco Archeologico del Colosseo’ in Rome, which aims to reconstruct ancient artifacts from their fragments. We built from scratch a synthetic dataset (DS) of fragments of different 3D objects including aging effects. We used this DS to train deep learning models for the task of classifying internal and external fragments. As model architectures, we adopted PointNet and dynamical graph convolutional neural network, which take as input a point cloud representing the spatial geometry of a fragment, and we optimized model performance by adding additional features sensitive to local geometry characteristics. We tested the approach by performing several experiments to check the robustness and generalization capabilities of the models. Finally, we test the models on a real case using a 3D scan of artifacts preserved in different museums, artificially fragmented, obtaining good performance.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

“…Both [7,8] deal with the reconstruction of broken artifacts by using a 3D acquisition set-up, transforming the objects into point clouds without the aid of neural networks. In particular, the first work aims to find the individual rigid transformations that better align all the fragments.…”

Section: Related Workmentioning

confidence: 99%

Artificial neural networks exploiting point cloud data for fragmented solid objects classification

Baiocchi,

Giagu,

Napoli

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Most publications of this field rely on the border irregularities and aim for precise alignment. They focus on automated reconstruction, such as [8,9,10] and consider jigsaw puzzle solving with missing fragments or with differently sized tiles [11,12,13]. These methods perform well on a small dataset with only one source of fragments.…”

Section: Puzzle Solvingmentioning

confidence: 99%

Image Reassembly Combining Deep Learning and Shortest Path Problem

Paumard

Picard

Tabia

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper addresses the problem of reassembling images from disjointed fragments. More specifically, given an unordered set of fragments, we aim at reassembling one or several possibly incomplete images. The main contributions of this work are: 1) several deep neural architectures to predict the relative position of image fragments that outperform the previous state of the art; 2) casting the reassembly problem into the shortest path in a graph problem for which we provide several construction algorithms depending on available information; 3) a new dataset of images taken from the Metropolitan Museum of Art (MET) dedicated to image reassembly for which we provide a clear setup and a strong baseline.

show abstract

“…Whether it comes to precisely align fragments or approximate a relative position, archaeological object reconstruction attracts numerous researchers, as shown by Rasheed and Nordin in [2,3]. When most reassembly work is based on semi-automated methods, some stands out by the use of automated reconstruction, such as [4,5,6,7]. These are mainly inspired by the research on puzzle solving, especially on jigsaw puzzles [8,9,10,11].…”

Section: Related Workmentioning

confidence: 99%

Jigsaw Puzzle Solving Using Local Feature Co-Occurrences in Deep Neural Networks

Paumard

Picard

Tabia

2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Archaeologists are in dire need of automated object reconstruction methods. Fragments reassembly is close to puzzle problems, which may be solved by computer vision algorithms. As they are often beaten on most image related tasks by deep learning algorithms, we study a classification method that can solve jigsaw puzzles. In this paper, we focus on classifying the relative position: given a couple of fragments, we compute their local relation (e.g. on top). We propose several enhancements over the state of the art in this domain, which is outperformed by our method by 25%. We propose an original dataset composed of pictures from the Metropolitan Museum of Art. We propose a greedy reconstruction method based on the predicted relative positions.

show abstract

3D puzzle reconstruction for archeological fragments

Cited by 7 publications

References 10 publications

Artificial neural networks exploiting point cloud data for fragmented solid objects classification

Artificial neural networks exploiting point cloud data for fragmented solid objects classification

Image Reassembly Combining Deep Learning and Shortest Path Problem

Jigsaw Puzzle Solving Using Local Feature Co-Occurrences in Deep Neural Networks

Contact Info

Product

Resources

About