A data-centric unsupervised 3D mesh segmentation method

2022-12-02
Tümer Sivri, Talya
Modeling, texture mapping, shape compression, simplification, and skeleton extracting are popular and essential topics in mesh segmentation applications. As it serves various purposes in computer science, the mesh segmentation problem is an active and prominent research area. With the help of growing machine learning, deep learning algorithms, and computation power, different methods have been applied to solve the 3D mesh segmentation problem more efficiently. In this thesis, we solve the 3D mesh segmentation problem from a different perspective. We present a novel data-centric AI approach for the segmentation of 3D meshes. We used node2vec, a semi-supervised learning algorithm, to train vector embedding representation for each node in a 3D mesh graph. This method makes the mesh data easier to process and more compact. In addition, we make dimension reduction with this method, which is very important for reducing computation costs and eliminating the curse of dimensionality. In other words, we learn information from nodes and edge connections between nodes. Then, the unsupervised learning algorithm K-Means was used to cluster each node according to node embedding information and two different initialization method was performed. Moreover, our data-centric approach is much lower in computational cost than complex models such as CNN and RNN. Instead of using complex and computationally expensive models, we apply data-centric methods to improve the raw data representation. The main contribution of this study is developing a data-centric AI framework by utilizing a node2vec embedding algorithm, machine learning, and deep learning techniques. Additionally, we adapt the cosine similarity method to compare and evaluate the node embedding vectors trained with different hyperparameters. Also, we developed a new algorithm for choosing the optimal cluster number, calculated with geodesic distance on the 3D mesh. Thus, we provide competitive results compared to the state-of-the-art mesh segmentation methods.

Suggestions

A Partition Based Method for Spectrum-Preserving Mesh Simplification
Yazgan, Misranur; Sahillioğlu, Yusuf; Department of Computer Engineering (2022-8-29)
When the complexity of a mesh starts introducing high computational costs, mesh simplification methods come into the picture, to reduce the number of elements utilized to represent the mesh. Majority of the simplification methods focus on preserving the appearance of the mesh, ignoring the spectral properties of the differential operators derived from the mesh. The spectrum of the Laplace-Beltrami operator is essential for a large subset of applications in geometry processing. Coarsening a mesh without cons...
IMPROVED PREDICTION FOR LAYERED PREDICTIVE ANIMATED MESH COMPRESSION
Bici, M. Oguz; Akar, Gözde (2010-09-29)
In this paper, we deal with layered predictive compression of animated meshes represented by series of 3D static meshes with same connectivity. We propose two schemes to improve the prediction. First improvement is using weighted spatial prediction rather than averaging neighbor vertices. The second improvement is a novel predictor based on rotation angle of incident triangles in current and previous frames. The experimental results show that around 6- 10 % bitrate reduction can be achieved by replacing the...
A probabilistic sparse skeleton based object detection
Altinoklu, Burak; Ulusoy, İlkay; Tarı, Zehra Sibel (Elsevier BV, 2016-11)
We present a Markov Random Field (MRF) based skeleton model for object shape and employ it in a probabilistic chamfer-matching framework for shape based object detection. Given an object category, shape hypotheses are generated from a set of sparse (coarse) skeletons guided by suitably defined unary and binary potentials at and between shape parts. The Markov framework assures that the generated samples properly reflect the observed or desired shape variability. As the model employs a sparsely sampled skele...
Multiple Description Coding of 3D Dynamic Meshes Based on Temporal Subsampling
Bici, M. Oguz; Akar, Gözde (2010-01-21)
In this paper, we propose a Multiple Description Coding (MDC) method for reliable transmission of compressed time consistent 3D dynamic meshes. It trades off reconstruction quality for error resilience to provide the best expected reconstruction of 3D mesh sequence at the decoder side. The method is based on partitioning the mesh frames into two sets by temporal subsampling and encoding each set independently by a 3D dynamic mesh coder. The encoded independent bitstreams or so-called descriptions are transm...
A shape deformation algorithm for constrained multidimensional scaling
Sahillioğlu, Yusuf (2015-12-01)
We present a new Euclidean embedding technique based on volumetric shape registration. Extrinsic representation of the intrinsic geometry of a shape is preferable in various computer graphics applications as it poses only a small degrees of freedom to deal with during processing. A popular Euclidean embedding approach to achieve such a representation is multidimensional scaling (MDS), which, however, distorts the original geometric details drastically. Our method introduces a constraint on the original MDS ...
Citation Formats
T. Tümer Sivri, “A data-centric unsupervised 3D mesh segmentation method,” M.S. - Master of Science, Middle East Technical University, 2022.