Solving archaeological puzzles
TL;DR: This paper presents a fully-automatic and general algorithm that addresses puzzle solving in archaeology, and shows that the state-of-the-art approach manages to correctly reassemble dozens of broken artifacts and frescoes.
Abstract: This paper focuses on the re-assembly of an archaeological artifact, given images of its fragments. This problem can be considered as a special challenging case of puzzle solving. The restricted case of re-assembly of a natural image from square pieces has been investigated extensively and was shown to be a difficult problem in its own right. Likewise, the case of matching “clean” 2D polygons/splines based solely on their geometric properties has been studied. But what if these ideal conditions do not hold? This is the problem addressed in the paper. Three unique characteristics of archaeological fragments make puzzle solving extremely difficult: (1) The fragments are of general shape; (2) They are abraded, especially at the boundaries (where the strongest cues for matching should exist); and (3) The domain of valid transformations between the pieces is continuous. The key contribution of this paper is a fully-automatic and general algorithm that addresses puzzle solving in this intriguing domain. We show that our approach manages to correctly reassemble dozens of broken artifacts and frescoes.
Citations
More filters
01 Jan 2002
TL;DR: In this paper, a method for the automatic reconstruction of a model based on the geometry of its parts, which may be computer-generated models or range-scanned models, is proposed.
Abstract: The problem of re-assembling an object from its parts or fragments has never been addressed with a unified computational approach, which depends on the pure geometric form of the parts and not on application-specific features. We propose a method for the automatic reconstruction of a model based on the geometry of its parts, which may be computer-generated models or range-scanned models. The matching process can benefit from any other external constraint imposed by the specific application.
6 citations
TL;DR: In this article, a metric learning-based deep convolutional neural network (CNN) was applied to an archaeological dataset to identify new query images according to similarities with known (training) images.
Abstract: Deep learning is a powerful tool for exploring large datasets and discovering new patterns. This work presents an account of a metric learning-based deep convolutional neural network (CNN) applied to an archaeological dataset. The proposed account speaks of three stages: training, testing/validating, and community detection. Several thousand artefact images, ranging from the Lower Palaeolithic period (1.4 million years ago) to the Late Islamic period (fourteenth century AD), were used to train the model (i.e., the CNN), to discern artefacts by site and period. After training, it attained a comparable accuracy to archaeologists in various periods. In order to test the model, it was called to identify new query images according to similarities with known (training) images. Validation blinding experiments showed that while archaeologists performed as well as the model within their field of expertise, they fell behind concerning other periods. Lastly, a community detection algorithm based on the confusion matrix data was used to discern affiliations across sites. A case-study on Levantine Natufian artefacts demonstrated the algorithm’s capacity to discern meaningful connections. As such, the model has the potential to reveal yet unknown patterns in archaeological data.
5 citations
3 citations
01 Sep 2022
TL;DR: In this article , a U-Net approach with a perceptual loss for the semantic inpainting of traditional Romanian vests was proposed to decide the most visually appropriate in-painting for very degraded historical items.
Abstract: It is impressive when one gets to see a hundreds or thousands years old artefact exhibited in the museum, whose appearance seems to have been untouched by centuries. Its restoration had been in the hands of a multidisciplinary team of experts and it had undergone a series of complex procedures. To this end, computational approaches that can support in deciding the most visually appropriate inpainting for very degraded historical items would be helpful as a second objective opinion for the restorers. The present paper thus attempts to put forward a U-Net approach with a perceptual loss for the semantic inpainting of traditional Romanian vests. Images taken of pieces from the collection of the Oltenia Museum in Craiova, along with such images with garments from the Internet, have been given to the deep learning model. The resulting numerical error for inpainting the corrupted parts is adequately low, however the visual similarity still has to be improved by considering further possibilities for finer tuning.
1 citations
TL;DR: In this article , the authors proposed a method to separate the fragments of different frescoes by treating this problem as a stylistic classification task, in which we have only parts of an artwork instead of a complete one.
Abstract: AbstractThe reconstruction of destroyed frescoes is a complex task: very small fragments, irregular shapes, color alterations and missing pieces are only some of the possible problems that we have to deal with. Surely, an important preliminary step involves the separation of mixed fragments. In fact, in a real scenario, such as a church destroyed by an earthquake, it is likely that pieces of different frescoes, which were close on the same wall, end up mixed together, making their reconstruction more complex. Their separation may be especially difficult if there are many of them and if there are no (or very old) reference images of the original frescoes. A possible way to separate the fragments is to treat this problem as a stylistic classification task, in which we have only parts of an artwork instead of a complete one. In this work, we tested various machine and deep learning solutions on the DAFNE dataset (to date the largest open access collection of artificially fragmented fresco images). The experiments showed promising results, with good performances in both binary and multi-class classification.KeywordsMachine learningDeep learningClassificationCultural HeritageFresco
1 citations
References
More filters
Book•
01 Jan 1990
TL;DR: This chapter discusses the configuration space of a Rigid Object, the challenges of dealing with uncertainty, and potential field methods for solving these problems.
Abstract: 1 Introduction and Overview.- 2 Configuration Space of a Rigid Object.- 3 Obstacles in Configuration Space.- 4 Roadmap Methods.- 5 Exact Cell Decomposition.- 6 Approximate Cell Decomposition.- 7 Potential Field Methods.- 8 Multiple Moving Objects.- 9 Kinematic Constraints.- 10 Dealing with Uncertainty.- 11 Movable Objects.- Prospects.- Appendix A Basic Mathematics.- Appendix B Computational Complexity.- Appendix C Graph Searching.- Appendix D Sweep-Line Algorithm.- References.
6,186 citations
"Solving archaeological puzzles" refers background in this paper
...We show how the set of valid transformation can be described as a configuration space problem, used in robotics [34]....
[...]
...The key idea of bypassing this procedure is to borrow the concept of a configuration space from the field of robotics [34]....
[...]
20 Jul 2017
TL;DR: This work presents a novel approach for image completion that results in images that are both locally and globally consistent, with a fully-convolutional neural network that can complete images of arbitrary resolutions by filling-in missing regions of any shape.
Abstract: We present a novel approach for image completion that results in images that are both locally and globally consistent. With a fully-convolutional neural network, we can complete images of arbitrary resolutions by filling-in missing regions of any shape. To train this image completion network to be consistent, we use global and local context discriminators that are trained to distinguish real images from completed ones. The global discriminator looks at the entire image to assess if it is coherent as a whole, while the local discriminator looks only at a small area centered at the completed region to ensure the local consistency of the generated patches. The image completion network is then trained to fool the both context discriminator networks, which requires it to generate images that are indistinguishable from real ones with regard to overall consistency as well as in details. We show that our approach can be used to complete a wide variety of scenes. Furthermore, in contrast with the patch-based approaches such as PatchMatch, our approach can generate fragments that do not appear elsewhere in the image, which allows us to naturally complete the images of objects with familiar and highly specific structures, such as faces.
1,961 citations
"Solving archaeological puzzles" refers background in this paper
...Several approaches have been proposed to extrapolation [28, 29, 30, 31, 32]....
[...]
TL;DR: This article develops methods for determining visually appealing motion transitions using linear blending, and assess the importance of these techniques by determining the minimum sensitivity of viewers to transition durations, the just noticeable difference, for both center-aligned and start-end specifications.
Abstract: This article develops methods for determining visually appealing motion transitions using linear blending. Motion transitions are segues between two sequences of animation, and are important components for generating compelling animation streams in virtual environments and computer games. Methods involving linear blending are studied because of their efficiency, computational speed, and widespread use. Two methods of transition specification are detailed, center-aligned and start-end transitions. First, we compute a set of optimal weights for an underlying cost metric used to determine the transition points. We then evaluate the optimally weighted cost metric for generalizability, appeal, and robustness through a cross-validation and user study. Next, we develop methods for computing visually appealing blend lengths for two broad categories of motion. We empirically evaluate these results through user studies. Finally, we assess the importance of these techniques by determining the minimum sensitivity of viewers to transition durations, the just noticeable difference, for both center-aligned and start-end specifications.
1,626 citations
08 Sep 2018
TL;DR: This work proposes the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels, and outperforms other methods for irregular masks.
Abstract: Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values in the masked holes (typically the mean value). This often leads to artifacts such as color discrepancy and blurriness. Post-processing is usually used to reduce such artifacts, but are expensive and may fail. We propose the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels. We further include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. Our model outperforms other methods for irregular masks. We show qualitative and quantitative comparisons with other methods to validate our approach.
1,606 citations
01 Jul 2012
TL;DR: This work presents a new method for synthesizing a transition region between two source images, such that inconsistent color, texture, and structural properties all change gradually from one source to the other, calling this process image melding.
Abstract: Current methods for combining two different images produce visible artifacts when the sources have very different textures and structures. We present a new method for synthesizing a transition region between two source images, such that inconsistent color, texture, and structural properties all change gradually from one source to the other. We call this process image melding. Our method builds upon a patch-based optimization foundation with three key generalizations: First, we enrich the patch search space with additional geometric and photometric transformations. Second, we integrate image gradients into the patch representation and replace the usual color averaging with a screened Poisson equation solver. And third, we propose a new energy based on mixed L2/L0 norms for colors and gradients that produces a gradual transition between sources without sacrificing texture sharpness. Together, all three generalizations enable patch-based solutions to a broad class of image melding problems involving inconsistent sources: object cloning, stitching challenging panoramas, hole filling from multiple photos, and image harmonization. In several cases, our unified method outperforms previous state-of-the-art methods specifically designed for those applications.
530 citations
"Solving archaeological puzzles" refers methods in this paper
...We adopt the example-based approach of [33], which manages to produce sharper and relatively more accurate extrapolations for our examples....
[...]