Graphical Models最新文献

Over the past decade, we have witnessed an enormous amount of research effort dedicated to the design of point cloud denoising techniques. In this article, we first provide a comprehensive survey on state-of-the-art denoising solutions, which are mainly categorized into three classes: filter-based, optimization-based, and deep learning-based techniques. Methods of each class are analyzed and discussed in detail. This is done using a benchmark on different denoising models, taking into account different aspects of denoising challenges. We also review two kinds of quality assessment methods designed for evaluating denoising quality. A comprehensive comparison is performed to cover several popular or state-of-the-art methods, together with insightful observations. Finally, we discuss open challenges and future research directions in identifying new point cloud denoising strategies.

Based on the Jacobi splitting of collocation matrices, we in this paper exploited the Jacobi–PIA format for bi-cubic B-spline surfaces. We first present the Jacobi–PIA scheme in term of matrix product, which has higher computational efficiency than that in term of matrix-vector product. To analyze the convergence of Jacobi–PIA, we transform the matrix product iterative scheme into the equivalent matrix-vector product scheme by using the properties of the Kronecker product. We showed that with the optimal relaxation factor, the Jacobi–PIA format for bi-cubic B-spline surface converges to the interpolation surface. Numerical results also demonstrated the effectiveness of the proposed method.

Layer-by-layer additive manufacturing is commonly utilized for additive manufacturing. Recent works utilize curved layers (rather than planar ones), on which print-paths are located, and outline their advantage over planar slicing. In this paper, free-form three-dimensional curves are utilized as input for the generation of print-paths, which covers the model to be printed and do not necessarily lie on either a planar or a curved layer. Such print-paths have been recently studied for 3-axis additive manufacturing, and a novel additive manufacturing process for the models represented using such curves are proposed for 4 and 5-axis additive manufacturing in this paper. The input curves are first subdivided into short sub-curves (i.e., segments), which are then merged to obtain print-paths with (collision-free) printing-head orientations along them. Thanks to additional two rotational axes of the printing-head, a less number of print-paths can potentially be obtained, which can reduce subdivisions in the input curves, and therefore, is desirable in additive manufacturing for improved mechanical properties in the printed parts. As a proof of concept, the print-paths with printing-head orientations along them are finally validated using an AM simulator and machine.

Context

The Bidirectional Reflectance Distribution Function (BRDF) represents a material through the incoming light on its surface. In this context, material clustering contributes to selecting a basis of representative BRDFs, the reconstruction of BRDFs, the personalization of the appearance of materials, and image-based estimation of material properties.

Objective

This work presents an approach to cluster a BRDF database according to its reflectance features.

Method

We first preprocess a BRDF database by mapping it to an image slice database and then find the best parameters for the LLE method through an empirical analysis, retrieving lower-dimensional databases. We performed a controlled experiment using the k-means, k-medoids, and spectral clustering algorithms applied to the low-dimensional databases.

Conclusion

K-means presented the best overall result compared to the other clustering algorithms. For applications that require cluster representatives from the database, we suggest using k-medoids, which presented results close to those of the k-means.

Discriminative and informative 3D shape descriptors are of fundamental significance to computer graphics applications, especially in the fields of geometry modeling and shape analysis. 3D shape descriptors, which reveal extrinsic/intrinsic properties of 3D shapes, have been well studied for decades and proved to be useful and effective in various analysis and synthesis tasks. Nonetheless, existing descriptors are mainly founded upon certain local differential attributes or global shape spectra, and certain combinations of both types. Conventional descriptors are typically customized for specific tasks with priori domain knowledge, which severely prevents their applications from widespread use. Recently, neural networks, benefiting from their powerful data-driven capability for general feature extraction from raw data without any domain knowledge, have achieved great success in many areas including shape analysis. In this paper, we present a novel hybrid fusion network (HFN) that learns multi-scale and multi-level shape representations via uniformly integrating a traditional region-based descriptor with modern neural networks. On one hand, we exploit the spectral graph wavelets (SGWs) to extract the shapes’ local-to-global features. On the other hand, the shapes are fed into a convolutional neural network to generate multi-level features simultaneously. Then a hierarchical fusion network learns a general and unified representation from these two different types of features which capture multi-scale and multi-level properties of the underlying shapes. Extensive experiments and comprehensive comparisons demonstrate our HFN can achieve better performance in common shape analysis tasks, such as shape retrieval and recognition, and the learned hybrid descriptor is robust, informative, and discriminative with more potential for widespread applications.

In recent years, approaches based on graph convolutional networks (GCNs) have achieved state-of-the-art performance in point cloud learning. The typical pipeline of GCNs is modeled as a two-stage learning process: graph construction and feature learning. We argue that such process exhibits low efficiency because a high percentage of the total time is consumed during the graph construction process when a large amount of sparse data are required to be accessed rather than on actual feature learning. To alleviate this problem, we propose a graph-based parallel branch network (Graph-PBN) that introduces a parallel branch structure to point cloud learning in this study. In particular, Graph-PBN is composed of two branches: the PointNet branch and the GCN branch. PointNet exhibits advantages in memory access and computational cost, while GCN behaves better in local context modeling. The two branches are combined in our architecture to utilize the potential of PointNet and GCN fully, facilitating the achievement of efficient and accurate recognition results. To better aggregate the features of each node in GCN, we investigate a novel operator, called EAGConv, to augment their local context by fully utilizing geometric and semantic features in a local graph. We conduct experiments on several benchmark datasets, and experiment results validate the significant performance of our method compared with other state-of-the-art approaches. Our code will be made publicly available at https://github.com/zhangcheng828/Graph-PBN.

The appearance styles of natural terrains vary significantly from region to region in real world, and there is a strong need to effectively produce realistic terrain with certain style in computer graphics. In this paper, we advocate a novel neural network approach to the rapid synthesis of multi-style terrains that could directly learn and infer from real terrain data. The key idea is to explicitly devise a conditional generative adversarial network (GAN) which encourages and favors the maximum-distance embedding of acquired styles in the latent space. Towards this functionality, we first collect a dataset that exhibits apparent terrain style diversity in their style attributes. Second, we design multiple discriminators that can distinguish different terrain styles. Third, we employ discriminators to extract terrain features in different spatial scales, so that the developed generator can produce new terrains by fusing the finer-scale and coarser-scale styles. In our experiments, we collect 10 typical terrain datasets from real terrain data that cover a wide range of regions. Our approach successfully generates realistic terrains with global-to-local style control. The experimental results have confirmed our neural network can produce natural terrains with high fidelity, which are user-friendly to style interpolation and style mixing for the terrain authoring task.

An algorithm was proposed to simulate the withering deformation of plant leaves by wrinkle and curl due to dehydration, based on cell dynamics and time-varying external force. First, a leaf boundary expansion algorithm was proposed to locate the feature points on the tip of the vein and construct the primary vein using a discrete geodesic path. Second, a novel mass-spring system by cell dynamics and a non-uniform mass distribution was defined to accelerate the movement of the boundary cells. Third, the cell swelling force was defined and adjusted to generate wrinkle deformation along with dehydration. Fourth, the time-varying external force on the feature points was defined to generate the curl deformation by adjusting the initial value of the external force and multiple iterative parameters. The implicit midpoint method was used to solve the equation of motion. The experimental results showed that our algorithm could simulate the wrinkle and curl deformation caused by dehydration and withering of leaves with high authenticity.

The vast majority of mesh-based modelling applications iteratively transform the mesh vertices under prescribed geometric conditions. This occurs in particular in methods cycling through the constraint set such as Position-Based Dynamics (PBD). A common case is the approximate local area preservation of triangular 2D meshes under external editing constraints. At the constraint level, this yields the nonconvex optimal triangle projection under prescribed area problem, for which there does not currently exist a direct solution method. In current PBD implementations, the area preservation constraint is linearised. The solution comes out through the iterations, without a guarantee of optimality, and the process may fail for degenerate inputs where the vertices are colinear or colocated. We propose a closed-form solution method and its numerically robust algebraic implementation. Our method handles degenerate inputs through a two-case analysis of the problem’s generic ambiguities. We show in a series of experiments in area-based 2D mesh editing that using optimal projection in place of area constraint linearisation in PBD speeds up and stabilises convergence.

Machine knitted textiles are complex multi-scale material structures increasingly important in many industries, including consumer products, architecture, composites, medical, and military. Computational modeling, simulation, and design of industrial fabrics require efficient representations of the spatial, material, and physical properties of such structures. We propose a process-oriented representation, TopoKnit, that defines a foundational data structure for representing the topology of weft-knitted textiles at the yarn scale. Process space serves as an intermediary between the machine and fabric spaces, and supports a concise, computationally efficient evaluation approach based on on-demand, near constant-time queries. In this paper, we define the properties of the process space, and design a data structure to represent it and algorithms to evaluate it. We demonstrate the effectiveness of the representation scheme by providing results of evaluations of the data structure in support of common topological operations in the fabric space.