Computer Aided Geometric Design最新文献

High-order mesh optimization has many goals, such as improving smoothness, reducing approximation error, and improving mesh quality. The previous methods do not optimize these objectives together, resulting in suboptimal results. To this end, we propose a multi-objective optimization method for high-order meshes. Central to our algorithm is using the multi-objective genetic algorithm (MOGA) to adapt to the multiple optimization objectives. Specifically, we optimize each control point one by one, where the MOGA is applied. We demonstrate the feasibility and effectiveness of our method over various models. Compared to other state-of-the-art methods, our method achieves a favorable trade-off between multiple objectives.

Recent advancements in shrink-wrapping-based mesh approximation have shown tremendous advantages for non-manifold defective meshes. However, these methods perform unsatisfactorily when maintaining the regions with sharp features and rich details of the input mesh. We propose an adaptive shrink-wrapping method based on the recent Alpha Wrapping technique, offering improved feature preservation while handling defective inputs. The proposed approach comprises three main steps. First, we compute a new sizing field with the capability to assess the discretization density of non-manifold defective meshes. Then, we generate a mesh feature skeleton by projecting input feature lines onto the offset surface, ensuring the preservation of sharp features. Finally, an adaptive wrapping approach based on normal projection is applied to preserve the regions with sharp features and rich details simultaneously. By conducting experimental tests on various datasets including Thingi10k, ABC, and GrabCAD, we demonstrate that our method exhibits significant improvements in mesh fidelity compared to the Alpha Wrapping method, while maintaining the advantage of manifold property inherited from shrink-wrapping methods.

3D mesh denoising is a crucial pre-processing step in many graphics applications. However, existing data-driven mesh denoising models, primarily trained on synthetic white noise, are less effective when applied to real-world meshes with the noise of complex intensities and distributions. Moreover, how to comprehensively capture information from input meshes and apply suitable denoising models for feature-preserving mesh denoising remains a critical and unresolved challenge. This paper presents a rotation-Equivariant model-based Mesh Denoising (EMD) model and a Realistic Mesh Noise Generation (RMNG) model to address these issues. Our EMD model leverages rotation-equivariant features and self-attention weights of geodesic patches for more effective feature extraction, thereby achieving SOTA denoising results. The RMNG model, based on the Generative Adversarial Networks (GANs) architecture, generates massive amounts of realistic noisy and noiseless mesh pairs data for data-driven mesh denoising model training, significantly benefiting real-world denoising tasks. To address the smooth degradation and loss of sharp edges commonly observed in captured meshes, we further introduce varying levels of Laplacian smoothing to input meshes during the paired training data generation, endowing the trained denoising model with feature recovery capabilities. Experimental results demonstrate the superior performance of our proposed method in preserving fine-grained features while removing noise on real-world captured meshes.

Current infrared and visible image fusion (IVIF) methods lack ground truth and require prior knowledge to guide the feature fusion process. However, in the fusion process, these features have not been placed in an equal and well-defined position, which causes the degradation of image quality. To address this challenge, this study develops a new end-to-end model, termed unpaired high-quality image-guided generative adversarial network (UHG-GAN). Specifically, we introduce the high-quality image as the reference standard of the fused image and employ a global discriminator and a local discriminator to identify the distribution difference between the high-quality image and the fused image. Through adversarial learning, the generator can generate images that are more consistent with high-quality expression. In addition, we also designed the laplacian pyramid augmentation (LPA) module in the generator, which integrates multi-scale features of source images across domains so that the generator can more fully extract the structure and texture information. Extensive experiments demonstrate that our method can effectively preserve the target information in the infrared image and the scene information in the visible image and significantly improve the image quality.

We propose a novel method to generate high-quality triangular meshes with specified anisotropy. Central to our algorithm is to present metric-adapted embeddings for converting the anisotropic meshing problem to an isotropic meshing problem with constant density. Moreover, the orientation of the input Riemannian metric forms a field, enabling us to use field-based meshing techniques to improve regularity and penalize obtuse angles. To achieve such metric-adapted embeddings, we use the cone singularities, which are generated to adapt to the input Riemannian metric. We demonstrate the feasibility and effectiveness of our method over various models. Compared to other state-of-the-art methods, our method achieves higher quality on all metrics in most models.

We propose a new method for generating tetrahedralizations for 3D surface meshes. The method builds upon a segmentation of the mesh that forms a rooted skeleton structure. Each segment in the structure is fitted with a stamp - a predefined basic shape with a regular and well-defined topology. After molding each stamp to the shape of the segment it is assigned to, we connect the segments with a layer of tetrahedra using a new approach to stitching two triangulated surfaces with tetrahedra. Our method not only generates a tetrahedralization with regular topology mimicking a bone-like structure with tissue being grouped around it, but also achieves running times that would allow for real-time usages. The running time of the method is closely correlated with the density of the input mesh which allows for controlling the expected time by decreasing the vertex count while still preserving the general shape of the object.

Signed Distance Fields (SDFs) have found widespread utility in collision detection applications due to their superior query efficiency and ability to represent continuous geometries. However, little attention has been paid to calculating the intersection of two arbitrary SDFs. In this paper, we propose a novel, accurate, and real-time approach for SDF-based collision detection between two solids, both represented as SDFs. Our primary strategy entails using interval calculations and the SDF gradient to guide the search for intersection points within the geometry. For arbitrary objects, we take inspiration from existing collision detection pipelines and segment the two SDFs into multiple parts with bounding volumes. Once potential collisions between two parts are identified, our method quickly computes comprehensive intersection information such as penetration depth, contact points, and contact normals. Our method is general in that it accepts both continuous and discrete SDF representations. Experiment results show that our method can detect collisions in high-precision models in real time, highlighting its potential for a wide range of applications in computer graphics and virtual reality.

Feature Recognition (FR) plays a crucial role in modern digital manufacturing, serving as a key technology for integrating Computer-Aided Design (CAD), Computer-Aided Process Planning (CAPP) and Computer-Aided Manufacturing (CAM) systems. The emergence of deep learning methods in recent years offers a new approach to address challenges in recognizing highly intersecting features with complex geometric shapes. However, due to the high cost of labeling real CAD models, neural networks are usually trained on computer-synthesized datasets, resulting in noticeable performance degradation when applied to real-world CAD models. Therefore, we propose a novel deep learning network, BrepMFR, designed for Machining Feature Recognition (MFR) from Boundary Representation (B-rep) models. We transform the original B-rep model into a graph representation as network-friendly input, incorporating local geometric shape and global topological relationships. Leveraging a graph neural network based on Transformer architecture and graph attention mechanism, we extract the feature representation of high-level semantic information to achieve machining feature recognition. Additionally, employing a two-step training strategy under a transfer learning framework, we enhance BrepMFR's generalization ability by adapting synthetic training data to real CAD data. Furthermore, we establish a large-scale synthetic CAD model dataset inclusive of 24 typical machining features, showcasing diversity in geometry that closely mirrors real-world mechanical engineering scenarios. Extensive experiments across various datasets demonstrate that BrepMFR achieves state-of-the-art machining feature recognition accuracy and performs effectively on CAD models of real-world mechanical parts.

A point cloud is a set of discrete surface samples. As the simplest 3D representation, it is widely used in 3D reconstruction and perception. Yet developing a generative model for point clouds remains challenging due to the sparsity and irregularity of points. Drawn by StyleGAN, the forefront image generation model, this paper presents Point-StyleGAN, a generator adapted from StyleGAN2 architecture for point cloud synthesis. Specifically, we replace all the 2D convolutions with 1D ones and introduce a series of multi-resolution discriminators to overcome the under-constrained issue caused by the sparsity of points. We further add a metric learning-based loss to improve generation diversity. Besides the generation task, we show several applications based on GAN inversion, among which an inversion encoder Point-pSp is designed and applied to point cloud reconstruction, completion, and interpolation. To our best knowledge, Point-pSp is the first inversion encoder for point cloud embedding in the latent space of GANs. The comparisons to prior work and the applications of GAN inversion demonstrate the advantages of our method. We believe the potential brought by the Point-StyleGAN architecture would further inspire massive follow-up works.

The aesthetic appeal and removability of clear aligners have led to their widespread popularity in orthodontic treatments. Dental attachments significantly contribute to shortening treatment duration and enhancing orthodontic outcomes. The automation of tailor-made dental attachments for individual teeth plays a crucial role in the field of orthodontics. This is because they enable more precise control over the forces applied, thereby effectively facilitating tooth movement. This study introduces an automated algorithm that generates dental attachments based on the orthodontic path. The algorithm automatically selects and places the appropriate type of attachment according to the magnitude of rotation and translation of teeth during orthodontic procedures. It adjusts the position and posture of the attachments to fit the teeth accurately. To validate the effectiveness of automatically placed attachments in guiding teeth along the predetermined path, this study employs finite element analysis to simulate the impact of attachments on teeth. Comparative analyses between the automated method and traditional manual techniques show that the proposed algorithm significantly enhances the precision and efficiency of attachment placement. Additionally, finite element simulations confirm the feasibility and effectiveness of this approach in clinical orthodontic applications, providing a novel technical pathway for automating attachment placement in orthodontic treatments and offering significant practical value for personalized and efficient orthodontic care.