A mesh editing framework is presented in this paper, which integrates Free-Form Deformation (FFD) and geometry signal processing. By using simplified model from original mesh, the editing task can be accomplished with...A mesh editing framework is presented in this paper, which integrates Free-Form Deformation (FFD) and geometry signal processing. By using simplified model from original mesh, the editing task can be accomplished with a few operations. We take the deformation of the proxy and the position coordinates of the mesh models as geometry signal. Wavelet analysis is em- ployed to separate local detail information gracefully. The crucial innovation of this paper is a new adaptive regular sampling approach for our signal analysis based editing framework. In our approach, an original mesh is resampled and then refined itera- tively which reflects optimization of our proposed spectrum preserving energy. As an extension of our spectrum editing scheme, the editing principle is applied to geometry details transferring, which brings satisfying results.展开更多
Subdivision is a widely used technique for mesh refinement.Classic methods rely on fixed manually defined weighting rules and struggle to generate a finer mesh with appropriate details,while advanced neural subdivisio...Subdivision is a widely used technique for mesh refinement.Classic methods rely on fixed manually defined weighting rules and struggle to generate a finer mesh with appropriate details,while advanced neural subdivision methods achieve data-driven nonlinear subdivision but lack robustness,suffering from limited subdivision levels and artifacts on novel shapes.To address these issues,this paper introduces a neural mesh refinement(NMR)method that uses the geometric structural priors learned from fine meshes to adaptively refine coarse meshes through subdivision,demonstrating robust generalization.Our key insight is that it is necessary to disentangle the network from non-structural information such as scale,rotation,and translation,enabling the network to focus on learning and applying the structural priors of local patches for adaptive refinement.For this purpose,we introduce an intrinsic structure descriptor and a locally adaptive neural filter.The intrinsic structure descriptor excludes the non-structural information to align local patches,thereby stabilizing the input feature space and enabling the network to robustly extract structural priors.The proposed neural filter,using a graph attention mechanism,extracts local structural features and adapts learned priors to local patches.Additionally,we observe that Charbonnier loss can alleviate over-smoothing compared to L2 loss.By combining these design choices,our method gains robust geometric learning and locally adaptive capabilities,enhancing generalization to various situations such as unseen shapes and arbitrary refinement levels.We evaluate our method on a diverse set of complex three-dimensional(3D)shapes,and experimental results show that it outperforms existing subdivision methods in terms of geometry quality.See https://zhuzhiwei99.github.io/NeuralMeshRefinement for the project page.展开更多
Point cloud completion aims to infer complete point clouds based on partial 3D point cloud inputs.Various previous methods apply coarseto-fine strategy networks for generating complete point clouds.However,such method...Point cloud completion aims to infer complete point clouds based on partial 3D point cloud inputs.Various previous methods apply coarseto-fine strategy networks for generating complete point clouds.However,such methods are not only relatively time-consuming but also cannot provide representative complete shape features based on partial inputs.In this paper,a novel feature alignment fast point cloud completion network(FACNet)is proposed to directly and efficiently generate the detailed shapes of objects.FACNet aligns high-dimensional feature distributions of both partial and complete point clouds to maintain global information about the complete shape.During its decoding process,the local features from the partial point cloud are incorporated along with the maintained global information to ensure complete and time-saving generation of the complete point cloud.Experimental results show that FACNet outperforms the state-of-theart on PCN,Completion3D,and MVP datasets,and achieves competitive performance on ShapeNet-55 and KITTI datasets.Moreover,FACNet and a simplified version,FACNet-slight,achieve a significant speedup of 3–10 times over other state-of-the-art methods.展开更多
Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth labels.However,in practice,it is not always feasible to obtain clean poi...Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth labels.However,in practice,it is not always feasible to obtain clean point clouds.In this paper,we introduce a novel unsupervised point cloud denoising method that eliminates the need to use clean point clouds as groundtruth labels during training.We demonstrate that it is feasible for neural networks to only take noisy point clouds as input,and learn to approximate and restore their clean versions.In particular,we generate two noise levels for the original point clouds,requiring the second noise level to be twice the amount of the first noise level.With this,we can deduce the relationship between the displacement information that recovers the clean surfaces across the two levels of noise,and thus learn the displacement of each noisy point in order to recover the corresponding clean point.Comprehensive experiments demonstrate that our method achieves outstanding denoising results across various datasets with synthetic and real-world noise,obtaining better performance than previous unsupervised methods and competitive performance to current supervised methods.展开更多
In this paper, an effective system for synthesizing animal skin patterns on arbitrary polygonal surfaces is developed. To accomplish the task, a system inspired by the Clonal Mosaic （CM） model is proposed. The CM mo...In this paper, an effective system for synthesizing animal skin patterns on arbitrary polygonal surfaces is developed. To accomplish the task, a system inspired by the Clonal Mosaic （CM） model is proposed. The CM model simulates cells＇ reactions on arbitrary surface. By controlling the division, mutation and repulsion of cells, a regulated spatial arrangement of cells is formed. This arrangement of cells shows appealing result, which is comparable with those natural patterns observed from animal skin. However, a typical CM simulation process incurs high computational cost, where the distances among ceils across a polygonal surface are measured and the movements of cells are constrained on the surface. In this framework, an approach is proposed to transform each of the original 3D geometrical planes of the surface into its Canonical Reference Plane Structure. This structure helps to simplify a 3D computational problem into a more manageable 2D problem. Furthermore, the concept of Local Relaxation is developed to optimally enhance the relaxation process for a typical CM simulation. The performances of the proposed solution methods have been verified with extensive experimental results.展开更多
Various types of cutting tools are known and are in use for machining parts. The dimensional parameters associated with cutting tools need to be estimated and compared to the desired values for determining their cutti...Various types of cutting tools are known and are in use for machining parts. The dimensional parameters associated with cutting tools need to be estimated and compared to the desired values for determining their cutting performance. In this paper, a data analysis methodology for extracting parameters from a measured point set corresponding to the surface of a cutting tool is provided. We propose that the 3-D data can be simplified into 2-D data or regular data by virtually slicing it at a predetermined section or by projecting it onto a same axial plane after a simple fixed-axis rotation. A plurality of curves can be generated and optimized based on the obtained 2-D points on a cross section for calculating the section parameters, including radial (axial) rake angle, relief angle, and land width. Other dimensional parameters can also be extracted from the contour of the presented rotary axial projection data. The experimental results have shown that the approaches elaborated in this paper are effective and robust, which can be potentially extended to other applications such as the inspection of similar parts and their parameters extraction.展开更多
In this paper,we tackle the challenging problem of point cloud completion from the perspective of feature learning.Our key observation is that to recover the underlying structures as well as surface details,given part...In this paper,we tackle the challenging problem of point cloud completion from the perspective of feature learning.Our key observation is that to recover the underlying structures as well as surface details,given partial input,a fundamental component is a good feature representation that can capture both global structure and local geometric details.We accordingly first propose FSNet,a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map by learning multiple latent patterns from local regions.We then integrate FSNet into a coarse-to-fine pipeline for point cloud completion.Specifically,a 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point cloud.Next,a point cloud upsampling network is used to generate a dense point cloud from the partial input and the coarse intermediate output.To efficiently exploit local structures and enhance point distribution uniformity,we propose IFNet,a point upsampling module with a self-correction mechanism that can progressively refine details of the generated dense point cloud.We have conducted qualitative and quantitative experiments on ShapeNet,MVP,and KITTI datasets,which demonstrate that our method outperforms stateof-the-art point cloud completion approaches.展开更多
A deep learning approach is presented for heat transfer and pressure drop prediction of complex fin geometries generated using composite Bézier curves.Thermal design process includes iterative high fidelity simul...A deep learning approach is presented for heat transfer and pressure drop prediction of complex fin geometries generated using composite Bézier curves.Thermal design process includes iterative high fidelity simulation which is complex,computationally expensive,and time-consuming.With the advancement in machine learning algorithms as well as Graphics Processing Units(GPUs),parallel processing architecture of GPUs can be used to accelerate thermo-fluid simulation.In this study,Convolutional Neural Networks(CNNs)are used to predict results of Computational Fluid Dynamics(CFD)directly from topologies saved as images.A design space with a single fin as well as multiple morphable fins are studied.A comparison of Xception network and regular CNN is presented for the case with a single fin design.Results show that high accuracy in prediction is observed for single fin design particularly using Xception network.Xception network provides 98 percent accuracy in heat transfer and pressure drop prediction of the single fin design.Increasing the design freedom to multiple fins increases the error in prediction.This error,however,remains within three percent of the ground truth values which is valuable for design purpose.The presented predictive model can be used for innovative BREP-based fin design optimization in compact and high efficiency heat exchangers.展开更多
基金Project supported by the National Basic Research Program (973) of China (No. 2002CB312102), and the National Natural Science Foun-dation of China (Nos. 60021201, 60333010 and 60505001)
文摘A mesh editing framework is presented in this paper, which integrates Free-Form Deformation (FFD) and geometry signal processing. By using simplified model from original mesh, the editing task can be accomplished with a few operations. We take the deformation of the proxy and the position coordinates of the mesh models as geometry signal. Wavelet analysis is em- ployed to separate local detail information gracefully. The crucial innovation of this paper is a new adaptive regular sampling approach for our signal analysis based editing framework. In our approach, an original mesh is resampled and then refined itera- tively which reflects optimization of our proposed spectrum preserving energy. As an extension of our spectrum editing scheme, the editing principle is applied to geometry details transferring, which brings satisfying results.
基金Project supported by the National Natural Science Foundation of China(Nos.62071427 and U21B2004)。
文摘Subdivision is a widely used technique for mesh refinement.Classic methods rely on fixed manually defined weighting rules and struggle to generate a finer mesh with appropriate details,while advanced neural subdivision methods achieve data-driven nonlinear subdivision but lack robustness,suffering from limited subdivision levels and artifacts on novel shapes.To address these issues,this paper introduces a neural mesh refinement(NMR)method that uses the geometric structural priors learned from fine meshes to adaptively refine coarse meshes through subdivision,demonstrating robust generalization.Our key insight is that it is necessary to disentangle the network from non-structural information such as scale,rotation,and translation,enabling the network to focus on learning and applying the structural priors of local patches for adaptive refinement.For this purpose,we introduce an intrinsic structure descriptor and a locally adaptive neural filter.The intrinsic structure descriptor excludes the non-structural information to align local patches,thereby stabilizing the input feature space and enabling the network to robustly extract structural priors.The proposed neural filter,using a graph attention mechanism,extracts local structural features and adapts learned priors to local patches.Additionally,we observe that Charbonnier loss can alleviate over-smoothing compared to L2 loss.By combining these design choices,our method gains robust geometric learning and locally adaptive capabilities,enhancing generalization to various situations such as unseen shapes and arbitrary refinement levels.We evaluate our method on a diverse set of complex three-dimensional(3D)shapes,and experimental results show that it outperforms existing subdivision methods in terms of geometry quality.See https://zhuzhiwei99.github.io/NeuralMeshRefinement for the project page.
基金supported by the Zhuhai Industry-University-Research Project(No.2220004002411)National Key R&D Program of China(No.2021YFE0205700)+3 种基金Science and Technology Development Fund of Macao(Nos.0070/2020/AMJ,00123/2022/A3,and 0096/2023/RIA2)Zhuhai City Polytechnic Research Project(No.2024KYBS02)Shenzhen Science and Technology Innovation Committee(No.SGDX20220530111001006)the University of Macao under Grants MYRG(Nos.GRG2023-00061-FST UMDF and 2022-00084-FST)。
文摘Point cloud completion aims to infer complete point clouds based on partial 3D point cloud inputs.Various previous methods apply coarseto-fine strategy networks for generating complete point clouds.However,such methods are not only relatively time-consuming but also cannot provide representative complete shape features based on partial inputs.In this paper,a novel feature alignment fast point cloud completion network(FACNet)is proposed to directly and efficiently generate the detailed shapes of objects.FACNet aligns high-dimensional feature distributions of both partial and complete point clouds to maintain global information about the complete shape.During its decoding process,the local features from the partial point cloud are incorporated along with the maintained global information to ensure complete and time-saving generation of the complete point cloud.Experimental results show that FACNet outperforms the state-of-theart on PCN,Completion3D,and MVP datasets,and achieves competitive performance on ShapeNet-55 and KITTI datasets.Moreover,FACNet and a simplified version,FACNet-slight,achieve a significant speedup of 3–10 times over other state-of-the-art methods.
文摘Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth labels.However,in practice,it is not always feasible to obtain clean point clouds.In this paper,we introduce a novel unsupervised point cloud denoising method that eliminates the need to use clean point clouds as groundtruth labels during training.We demonstrate that it is feasible for neural networks to only take noisy point clouds as input,and learn to approximate and restore their clean versions.In particular,we generate two noise levels for the original point clouds,requiring the second noise level to be twice the amount of the first noise level.With this,we can deduce the relationship between the displacement information that recovers the clean surfaces across the two levels of noise,and thus learn the displacement of each noisy point in order to recover the corresponding clean point.Comprehensive experiments demonstrate that our method achieves outstanding denoising results across various datasets with synthetic and real-world noise,obtaining better performance than previous unsupervised methods and competitive performance to current supervised methods.
文摘In this paper, an effective system for synthesizing animal skin patterns on arbitrary polygonal surfaces is developed. To accomplish the task, a system inspired by the Clonal Mosaic （CM） model is proposed. The CM model simulates cells＇ reactions on arbitrary surface. By controlling the division, mutation and repulsion of cells, a regulated spatial arrangement of cells is formed. This arrangement of cells shows appealing result, which is comparable with those natural patterns observed from animal skin. However, a typical CM simulation process incurs high computational cost, where the distances among ceils across a polygonal surface are measured and the movements of cells are constrained on the surface. In this framework, an approach is proposed to transform each of the original 3D geometrical planes of the surface into its Canonical Reference Plane Structure. This structure helps to simplify a 3D computational problem into a more manageable 2D problem. Furthermore, the concept of Local Relaxation is developed to optimally enhance the relaxation process for a typical CM simulation. The performances of the proposed solution methods have been verified with extensive experimental results.
文摘Various types of cutting tools are known and are in use for machining parts. The dimensional parameters associated with cutting tools need to be estimated and compared to the desired values for determining their cutting performance. In this paper, a data analysis methodology for extracting parameters from a measured point set corresponding to the surface of a cutting tool is provided. We propose that the 3-D data can be simplified into 2-D data or regular data by virtually slicing it at a predetermined section or by projecting it onto a same axial plane after a simple fixed-axis rotation. A plurality of curves can be generated and optimized based on the obtained 2-D points on a cross section for calculating the section parameters, including radial (axial) rake angle, relief angle, and land width. Other dimensional parameters can also be extracted from the contour of the presented rotary axial projection data. The experimental results have shown that the approaches elaborated in this paper are effective and robust, which can be potentially extended to other applications such as the inspection of similar parts and their parameters extraction.
基金This work was supported by the National Natural Science Foundation of China(61872250,U2001206,U21B2023)the GD Natural Science Foundation(2021B1515020085)+2 种基金DEGP Innovation Team(2022KCXTD025)Shenzhen Science and Technology Innovation Program(JCYJ20210324120213036)Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ).
文摘In this paper,we tackle the challenging problem of point cloud completion from the perspective of feature learning.Our key observation is that to recover the underlying structures as well as surface details,given partial input,a fundamental component is a good feature representation that can capture both global structure and local geometric details.We accordingly first propose FSNet,a feature structuring module that can adaptively aggregate point-wise features into a 2D structured feature map by learning multiple latent patterns from local regions.We then integrate FSNet into a coarse-to-fine pipeline for point cloud completion.Specifically,a 2D convolutional neural network is adopted to decode feature maps from FSNet into a coarse and complete point cloud.Next,a point cloud upsampling network is used to generate a dense point cloud from the partial input and the coarse intermediate output.To efficiently exploit local structures and enhance point distribution uniformity,we propose IFNet,a point upsampling module with a self-correction mechanism that can progressively refine details of the generated dense point cloud.We have conducted qualitative and quantitative experiments on ShapeNet,MVP,and KITTI datasets,which demonstrate that our method outperforms stateof-the-art point cloud completion approaches.
文摘A deep learning approach is presented for heat transfer and pressure drop prediction of complex fin geometries generated using composite Bézier curves.Thermal design process includes iterative high fidelity simulation which is complex,computationally expensive,and time-consuming.With the advancement in machine learning algorithms as well as Graphics Processing Units(GPUs),parallel processing architecture of GPUs can be used to accelerate thermo-fluid simulation.In this study,Convolutional Neural Networks(CNNs)are used to predict results of Computational Fluid Dynamics(CFD)directly from topologies saved as images.A design space with a single fin as well as multiple morphable fins are studied.A comparison of Xception network and regular CNN is presented for the case with a single fin design.Results show that high accuracy in prediction is observed for single fin design particularly using Xception network.Xception network provides 98 percent accuracy in heat transfer and pressure drop prediction of the single fin design.Increasing the design freedom to multiple fins increases the error in prediction.This error,however,remains within three percent of the ground truth values which is valuable for design purpose.The presented predictive model can be used for innovative BREP-based fin design optimization in compact and high efficiency heat exchangers.
