Search

Archaeological steles having a rough surface due to long periods of weathering make recognizing the inscription difficult. In this paper, we propose a machine learning-based method to extract reliefs for the inscription from a rough stele surface. Relief candidate segments are initially obtained by using a curvature-based method, which include not only actual reliefs but also noises such as dents and scratches. Then, relief segments are selected using a support vector machine classifier that is trained with various features extracted from relief candidate segments. While conventional methods using a single geometric feature easily fail to detect reliefs from the rough surface, the proposed method utilizes 79-dimensional features consisting of appearance-based, cross section-based, and local extrema-based characteristics of each candidate segment to determine whether the segment is relief or not. Using the proposed method, the inscription of the stele Musul-ojakbi made during the Silla Dynasty AD578 were completely recognized. The experimental results demonstrate that the proposed method accurately extracts reliefs and achieves the highest performance on the rough stele data. The performance of the proposed method is about 8.95% and 10.4% higher than the best of the conventional methods in terms of the F1-score and the SIRI, respectively.

We present co-skeletons, a new method that computes consistent curve skeletons for 3D shapes from a given family. We compute co-skeletons in terms of sampling density and semantic relevance, while preserving the desired characteristics of traditional, per-shape curve skeletonization approaches. We take the curve skeletons extracted by traditional approaches for all shapes from a family as input, and compute semantic correlation information of individual skeleton branches to guide an edge-pruning process via skeleton-based descriptors, clustering, and a voting algorithm. Our approach achieves more concise and family-consistent skeletons when compared to traditional per-shape methods. We show the utility of our method by using co-skeletons for shape segmentation and shape blending on real-world data.

In this paper, we propose a Variational Auto-Encoder able to correctly reconstruct a fine mesh from a very low-dimensional latent space. The architecture avoids the usual coarsening of the graph and relies on pooling layers for the decoding phase and on the mean values of the training set for the up-sampling phase. We select new operators compared to previous work, and in particular, we define a new Dirac operator which can be extended to different types of graph structured data. We show the improvements over the previous operators and compare the results with the current benchmark on the Coma Dataset.

Body surface area (BSA) measurement is important in engineering and medicine fields to determine parameters for various applications. Three-dimensional scanning techniques may be used to acquire the BSA directly. Nevertheless, the raw data obtained from 3D scanning usually requires some manual post-processing which is time-consuming and requires technical expertise. Automated post-processing of 3D scans enables expedient BSA calculation with minimal technical expertise. The purpose of this research was to compare the accuracy and reliability of three different automated post-processing techniques including Stitched Puppet (SP), Poisson surface reconstruction (PSR), and screened Poisson surface reconstruction (SPSR) using manual post-processing as the criterion. Twenty-nine participants were scanned twice, and raw data were processed with the manual operation and automated techniques to acquire BSAs separately. The reliability of BSAs acquired from these approaches was represented by the relative technical error of measurements (TEM). Pearson’s regressions were applied to correct BSAs acquired from the automated techniques. The limits of agreement (LOA) were used to quantify the accuracy of BSAs acquired from the automated techniques and corrected by regression models. The reliability (relative TEM) of BSAs obtained from PSR, SPSR and SP were 0.32%, 0.30%, 0.82% respectively. After removing bias with the regression models, the LOA for PSR, SPSR and SP were (-0.0134 m2, 0.0135 m2), ±0.0131 m2, ±0.0573 m2 respectively. It is concluded that PSR and SPSR are good alternative approaches to manual post-processing for applications that need reliable and accurate measurements of BSAs with large populations.

Purpose This paper aims to investigate the feasibility of adding macro-textures to triangle meshes for additive manufacturing (AM) focusing on possible time and quality issues in both software processing and part fabrication. Design/methodology/approach A demonstrative software tool was developed to apply user-selected textures to existing meshes. The computational procedure is a three-dimensional extension of the solid texturing method used in computer graphics. The tool was tested for speed and quality of results, considering also the pre- and post-processing operations required. Some textured meshes were printed by different processes to test build speed and quality. Findings The tool can handle models with realistic complexity in acceptable computation times. Parts are built without difficulties or extra-costs achieving a good aesthetic yield of the texture. Research limitations/implications The tool cannot reproduce sample patterns but requires the development of a generation algorithm for different type of textures. Mesh processing operations may take a long time when very fine textures are added to large parts. Practical implications Direct texturing can help obtain parts with aesthetic or functional textures without the need for surface post-treatments, which can be especially difficult and expensive for plastic parts. Originality/value The proposed method improves the uniformity and consistency of textures compared to existing approaches, and can support future systematic studies on the detail resolution of AM processes.

Inspired by the recent growth of computational methods for general polygonal and polyhedral meshes, this paper introduces Cinolib: a novel header only C++ library for geometry processing. Cinolib differentiates itself from similar toolkits in that it is specifically designed to support a wide set of meshes, such as triangle, quadrilateral and general polygonal surface meshes, as well as tetrahedral, hexahedral and general polyhedral volumetric meshes. At the core of the library there is a hierarchical data structure that factorizes the common properties among the various meshes, allowing tools and algorithms to operate on the widest possible set of meshes with a single implementation, thus avoiding code repetition and facilitating bug fixing and software maintenance. Cinolib is licensed with MIT, it currently counts more than 50K lines of code and, besides the core structure, already comprises a vast set of widespread tools for computer graphics and engineering.

Nowadays digital replicas of artefacts belonging to the Cultural Heritage (CH) are one of the most promising innovations for museums exhibitions, since they foster new forms of interaction with collections, at different scales. However, practical digitization is still a complex task dedicated to specialized operators. Due to these premises, this paper introduces a novel approach to support non-experts working in museums with robust, easy-to-use workflows based on low-cost widespread devices, aimed at the study, classification, preservation, communication and restoration of CH artefacts. The proposed methodology introduces an automated combination of acquisition, based on mobile equipment and visualization, based on Real-Time Rendering. After the description of devices used along the workflow, the paper focuses on image pre-processing and geometry processing techniques adopted to generate accurate 3D models from photographs. Assessment criteria for the developed process evaluation are illustrated. Tests of the methodology on some effective museum case studies are presented and discussed.

In this paper, we present a method for 3D mesh segmentation based on sparse non-negative matrix factorization (NMF). Image analysis techniques based on NMF have been shown to decompose images into semantically meaningful local features. Since the features and coefficients are represented in terms of non-negative values, the features contribute to the resulting images in an intuitive, additive fashion. Like spectral mesh segmentation, our method relies on the construction of an affinity matrix which depends on the geometric properties of the mesh. We show that segmentation based on the NMF is simpler to implement, and can result in more meaningful segmentation results than spectral mesh segmentation.

Conformal parameterization of mesh models has numerous applications in geometry processing. Conformality is desirable for remeshing, surface reconstruction, and many other mesh processing applications. Subject to the conformality requirement, these applications typically benefit from parameterizations with smaller stretch. The Angle Based Flattening (ABF) method, presented a few years ago, generates provably valid conformal parameterizations with low stretch. However, it is quite time-consuming and becomes error prone for large meshes due to numerical error accumulation. This work presents ABF++, a highly efficient extension of the ABF method, that overcomes these drawbacks while maintaining all the advantages of ABF. ABF++ robustly parameterizes meshes of hundreds of thousands and millions of triangles within minutes. It is based on three main components: (1) a new numerical solution technique that dramatically reduces the dimension of the linear systems solved at each iteration, speeding up the solution; (2) a new robust scheme for reconstructing the 2D coordinates from the angle space solution that avoids the numerical instabilities which hindered the ABF reconstruction scheme; and (3) an efficient hierarchical solution technique. The speedup with (1) does not come at the expense of greater distortion. The hierarchical technique (3) enables parameterization of models with millions of faces in seconds at the expense of a minor increase in parametric distortion. The parameterization computed by ABF++ are provably valid, that is they contain no flipped triangles. As a result of these extensions, the ABF++ method is extremely suitable for robustly and efficiently parameterizing models for geometry-processing applications.