Search

As a significant geometric feature of 3D point clouds, sharp features play an important role in shape analysis, 3D reconstruction, registration, localization, etc. Current sharp feature detection methods are still sensitive to the quality of the input point cloud, and the detection performance is affected by random noisy points and non-uniform densities. In this paper, using the prior knowledge of geometric features, we propose a Multi-scale Laplace Network (MSL-Net), a new deep-learning-based method based on an intrinsic neighbor shape descriptor, to detect sharp features from 3D point clouds. First, we establish a discrete intrinsic neighborhood of the point cloud based on the Laplacian graph, which reduces the error of local implicit surface estimation. Then, we design a new intrinsic shape descriptor based on the intrinsic neighborhood, combined with enhanced normal extraction and cosine-based field estimation function. Finally, we present the backbone of MSL-Net based on the intrinsic shape descriptor. Benefiting from the intrinsic neighborhood and shape descriptor, our MSL-Net has simple architecture and is capable of establishing accurate feature prediction that satisfies the manifold distribution while avoiding complex intrinsic metric calculations. Extensive experimental results demonstrate that with the multi-scale structure, MSL-Net has a strong analytical ability for local perturbations of point clouds. Compared with state-of-the-art methods, our MSL-Net is more robust and accurate.

We present an effective spectral matching method based on a shape association graph for finding region correspondences between two cel animation keyframes. We formulate the correspondence problem as an adapted quadratic assignment problem, which comprehensively considers both the intrinsic geometric and topology of regions to find the globally optimal correspondence. To simultaneously represent the geometric and topological similarities between regions, we propose a shape association graph (SAG), whose node attributes indicate the geometric distance between regions, and whose edge attributes indicate the topological distance between combined region pairs. We convert topological distance to geometric distance between geometric objects with topological features of the pairs, and introduce Kendall shape space to calculate the intrinsic geometric distance. By utilizing the spectral properties of the affinity matrix induced by the SAG, our approach can efficiently extract globally optimal region correspondences, even if shapes have inconsistent topology and severe deformation. It is also robust to shapes undergoing similarity transformations, and compatible with parallel computing techniques.

This paper presents a method for simulating surface crack patterns appearing in ceramic glaze, glass, wood and mud. It uses a physically and heuristically combined method to model this type of crack pattern. A stress field is defined heuristically over the triangle mesh of an object. Then, a first-order quasi-static cracking node method (CNM) is used to model deformation. A novel combined stress and energy combined crack criterion is employed to address crack initiation and propagation separately according to physics. Meanwhile, a highest-stress-first rule is applied in crack initiation, and a breadth-first rule is applied in crack propagation. Finally, a local stress relaxation step is employed to evolve the stress field and avoid shattering artifacts. Other related issues are also discussed, such as the elimination of quadrature sub-cells, the prevention of parallel cracks and spurious crack procession. Using this method, a variety of crack patterns observed in the real world can be reproduced by changing a set of parameters. Consequently, our method is robust because the computational mesh is independent of dynamic cracks and has no sliver elements. We evaluate the realism of our results by comparing them with photographs of real-world examples. Further, we demonstrate the controllability of our method by varying different parameters.

The existing 3D modeling studies of Chinese ancient architecture are mostly procedure driven and rely on fixed construction rules. Therefore, these methods have limited applications in virtual reality (VR) engineering. We propose a data-driven approach to synthesize 3D models from existing 3D data that provides more flexibility and fills the gap between academic studies and VR engineering. First, 3D architecture models were preprocessed and decomposed into components, and the components were clustered by their geometric features. Second, a Bayesian network was generated by learning from the dataset to represent the internal relationships between the architectural components. Third, the inference results of the trained network were utilized to generate a reasonable relationship matching to support the synthesis of the structural components. The proposed method can be used in 3D content creation for VR development and directly supports VR applications in practice.

Surface segmentation and edge feature lines extraction from fractured fragments of relics are essential steps for computer assisted restoration of fragmented relics. As these fragments were heavily eroded, it is a challenging work to segment surface and extract edge feature lines. This paper presents a novel method to segment surface and extract edge feature lines from triangular meshes of irregular fractured fragments. Firstly, a rough surface segmentation is accomplished by using a clustering algorithm based on the vertex normal vector. Secondly, in order to differentiate between original and fracture faces, a novel integral invariant is introduced to compute the surface roughness. Thirdly, an accurate surface segmentation is implemented by merging faces based on face normal vector and roughness. Finally, edge feature lines are extracted based on the surface segmentation. Some experiments are made and analyzed, and the results show that our method can achieve surface segmentation and edge extraction effectively.

Abstract: Shape registration has a wide range of applications in geometric modeling, medical imaging, and computer vision. This paper focuses on the registration of the genus-3 vestibular systems and studies the geometric differences between the normal and Adolescent Idiopathic Scoliosis (AIS) groups. The non-trivial topology of the VS poses great technical challenges to the geometric analysis. To tackle these challenges, we present an effective and practical solution to register the vestibular systems. We first extract six geodesic landmarks for the VS, which are stable, intrinsic, and insensitive to the VS’s resolution and tessellation. Moreover, they are highly consistent regardless of the AIS and normal groups. The detected geodesic landmarks partition the VS into three patches, a topological annulus and two topological disks. For each pair of patches of the AIS subject and the control, we compute a bijective map using the holomorphic 1-form and harmonic map techniques. With a carefully designed boundary condition, the three individual maps can be glued in a seamless manner so that the resulting registration is a homeomorphism with exact landmark matching. Our method is robust, automatic and efficient. It takes only a few seconds on a low-end PC, which significantly outperforms the non-rigid ICP algorithm. We conducted a student’s t-test on the test data. Computational results show that using the mean curvature measure , our method can distinguish the AIS subjects and the normal subjects. [Copyright &y& Elsevier]

This paper presents a novel approach to automating the entire coloring process in traditional cel animation production. A feature-based region-matching algorithm is proposed. It first matches a set of master frames to construct correspondences between regions in the master frames and extract a stable topology. The first frame of each scene is then colored based on the set of master frames. With the painted first frame and established stable topology, each region in subsequent frames is matched with regions in the previous frames and colored. Compared with other algorithms, our approach is able to handle bigger changes between frames and automatically color the first frame of each sequence.