Pub Date : 2025-10-15DOI: 10.1016/j.cad.2025.103994
Kai Dai , Tianqi Song , Hangcheng Zhang , Yi-Jun Yang , Wei Zeng
Many computer graphics applications such as Boolean operation, visible surface determination, rendering, etc. require fast and robust computation of the relative positional relationships between points and shapes. The Line Segment Substitution (LSS) method presented in this paper is an improvement of the ray crossing method, which can effectively compute the positional relationship between a point and a closed planar shape. The boundary of the closed planar shape can be composed of line segments, conic curve segments, and spline curve segments. In the LSS method, complex curves will be directly replaced by line segments or replaced after iterative segmentation, depending on the type of curve and the positional relationship between the curve and target point. Then, the relationship between the point and the shape can be determined based on the parity of the number of intersections between a ray originating from the target point and the substitute line segments. Experiments have shown that, compared with other methods, the LSS method achieves the best efficiency and accuracy among methods that do not require preprocessing.
{"title":"An algorithm to compute the point inclusion of 2D planar shapes based on line segment substitution","authors":"Kai Dai , Tianqi Song , Hangcheng Zhang , Yi-Jun Yang , Wei Zeng","doi":"10.1016/j.cad.2025.103994","DOIUrl":"10.1016/j.cad.2025.103994","url":null,"abstract":"<div><div>Many computer graphics applications such as Boolean operation, visible surface determination, rendering, etc. require fast and robust computation of the relative positional relationships between points and shapes. The Line Segment Substitution (LSS) method presented in this paper is an improvement of the ray crossing method, which can effectively compute the positional relationship between a point and a closed planar shape. The boundary of the closed planar shape can be composed of line segments, conic curve segments, and spline curve segments. In the LSS method, complex curves will be directly replaced by line segments or replaced after iterative segmentation, depending on the type of curve and the positional relationship between the curve and target point. Then, the relationship between the point and the shape can be determined based on the parity of the number of intersections between a ray originating from the target point and the substitute line segments. Experiments have shown that, compared with other methods, the LSS method achieves the best efficiency and accuracy among methods that do not require preprocessing.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 103994"},"PeriodicalIF":3.1,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145364942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-14DOI: 10.1016/j.cad.2025.103992
Zhuo Zhang , Sen Zhang , Yuan Zhao , Wei Wang , Hongzhou Wu , Xi Yang , Canqun Yang
Physics-Informed Neural Networks (PINNs) have shown great promise for solving partial differential equations (PDEs), but their application to multi-dimensional problems often suffers from the curse of dimensionality, leading to exponential growth in computational and memory requirements. Moreover, accurately capturing complex local features, such as those found in fluid flows, remains a significant challenge for existing approaches. To address these challenges, we propose the Dynamic Feature Separation Physics-Informed Neural Network (DFS-PINN), which introduces an innovative input-decoupling and dynamic interaction mechanism. This approach reduces computational complexity from to , enabling efficient training and improved accuracy for multi-dimensional problems, especially in real-time rendering and fluid simulations. When applied to the lid-driven cavity flow problem, DFS-PINN achieves a 6 reduction in runtime and a 62 reduction in memory usage with collocation points, compared to standard PINNs. For large-scale datasets with over points, DFS-PINN attains a mean squared error (MSE) of 0.000122, showcasing its superior computational efficiency and predictive accuracy. These results position DFS-PINN as a scalable and robust framework for solving multi-dimensional PDEs, demonstrating substantial improvements in both computational efficiency and modeling accuracy.
{"title":"DFS-PINN: A Dynamic Feature Separation Physics-Informed Neural Network","authors":"Zhuo Zhang , Sen Zhang , Yuan Zhao , Wei Wang , Hongzhou Wu , Xi Yang , Canqun Yang","doi":"10.1016/j.cad.2025.103992","DOIUrl":"10.1016/j.cad.2025.103992","url":null,"abstract":"<div><div>Physics-Informed Neural Networks (PINNs) have shown great promise for solving partial differential equations (PDEs), but their application to multi-dimensional problems often suffers from the curse of dimensionality, leading to exponential growth in computational and memory requirements. Moreover, accurately capturing complex local features, such as those found in fluid flows, remains a significant challenge for existing approaches. To address these challenges, we propose the Dynamic Feature Separation Physics-Informed Neural Network (DFS-PINN), which introduces an innovative input-decoupling and dynamic interaction mechanism. This approach reduces computational complexity from <span><math><mrow><mi>O</mi><mrow><mo>(</mo><msup><mrow><mi>N</mi></mrow><mrow><mi>d</mi></mrow></msup><mo>)</mo></mrow></mrow></math></span> to <span><math><mrow><mi>O</mi><mrow><mo>(</mo><mi>N</mi><mo>×</mo><mi>d</mi><mo>)</mo></mrow></mrow></math></span>, enabling efficient training and improved accuracy for multi-dimensional problems, especially in real-time rendering and fluid simulations. When applied to the lid-driven cavity flow problem, DFS-PINN achieves a 6<span><math><mo>×</mo></math></span> reduction in runtime and a 62<span><math><mo>×</mo></math></span> reduction in memory usage with <span><math><msup><mrow><mn>2</mn></mrow><mrow><mn>15</mn></mrow></msup></math></span> collocation points, compared to standard PINNs. For large-scale datasets with over <span><math><msup><mrow><mn>2</mn></mrow><mrow><mn>20</mn></mrow></msup></math></span> points, DFS-PINN attains a mean squared error (MSE) of 0.000122, showcasing its superior computational efficiency and predictive accuracy. These results position DFS-PINN as a scalable and robust framework for solving multi-dimensional PDEs, demonstrating substantial improvements in both computational efficiency and modeling accuracy.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 103992"},"PeriodicalIF":3.1,"publicationDate":"2025-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-13DOI: 10.1016/j.cad.2025.103993
Yong Zhang , Yongfei Wang , Tao Wu , Ye Xu , Chen Li
A novel isoparametric tool path generation strategy incorporating spacing control was developed to overcome machining challenges in complex dental restoration fabrication, with particular emphasis on mitigating undercut formation and minimizing tool wear. To enhance machining efficiency and accuracy, a preprocessing strategy was introduced for prioritized reconstruction of offset surfaces, facilitating spiral trajectory parameterization. A segmented 3D-to-2D mapping algorithm was developed, achieving a 44.43 % reduction in computational time while maintaining machining precision. The formation mechanism of undercuts in dental restoration structures was systematically analyzed. Based on this analysis, a surface formation prediction algorithm was established to accurately identify undercut areas in cavity regions after machining. This enables the implementation of localized overcut strategies to replace conventional global undercut approaches, thereby improving the fitting accuracy and stability of dental restorations. The wear characteristics of ball-end grinding wheels were investigated, with particular focus on the relationship between spiral trajectory spacing and tool wear. In undercut regions, the machining allowance was observed to significantly affect cutting depth, leading to increased grinding forces and accelerated tool wear. To mitigate this effect, a localized spacing reduction strategy was proposed, which effectively minimizes tool wear while only slightly increasing machining time. The effectiveness of the proposed methodology was verified through precision grinding experiments on complex dental restoration structures. These methods have the potential to be applied to a wide range of complex 3D machining and manufacturing problems.
{"title":"Iso-parametric path planning to mitigate wheel wear in grinding of complex dental crowns","authors":"Yong Zhang , Yongfei Wang , Tao Wu , Ye Xu , Chen Li","doi":"10.1016/j.cad.2025.103993","DOIUrl":"10.1016/j.cad.2025.103993","url":null,"abstract":"<div><div>A novel isoparametric tool path generation strategy incorporating spacing control was developed to overcome machining challenges in complex dental restoration fabrication, with particular emphasis on mitigating undercut formation and minimizing tool wear. To enhance machining efficiency and accuracy, a preprocessing strategy was introduced for prioritized reconstruction of offset surfaces, facilitating spiral trajectory parameterization. A segmented 3D-to-2D mapping algorithm was developed, achieving a 44.43 % reduction in computational time while maintaining machining precision. The formation mechanism of undercuts in dental restoration structures was systematically analyzed. Based on this analysis, a surface formation prediction algorithm was established to accurately identify undercut areas in cavity regions after machining. This enables the implementation of localized overcut strategies to replace conventional global undercut approaches, thereby improving the fitting accuracy and stability of dental restorations. The wear characteristics of ball-end grinding wheels were investigated, with particular focus on the relationship between spiral trajectory spacing and tool wear. In undercut regions, the machining allowance was observed to significantly affect cutting depth, leading to increased grinding forces and accelerated tool wear. To mitigate this effect, a localized spacing reduction strategy was proposed, which effectively minimizes tool wear while only slightly increasing machining time. The effectiveness of the proposed methodology was verified through precision grinding experiments on complex dental restoration structures. These methods have the potential to be applied to a wide range of complex 3D machining and manufacturing problems.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 103993"},"PeriodicalIF":3.1,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-13DOI: 10.1016/j.cad.2025.103990
Yu-Chou Chiang , Hui Wang , Xinye Li , Helmut Pottmann
A self-Airy membrane shell is a special type of shell structure whose shape coincides with the shell’s Airy stress surface. It provides the convenient property that any polyhedral discretization of such a surface will automatically generate a mesh in funicular equilibrium. A self-Airy shell designed for a uniform vertical load would simply have a constant isotropic Gaussian curvature. However, a challenge in implementing a self-Airy shell in architecture is the lack of a design method, especially in designing unreinforced boundaries. Those are singular planar curves, where the two principal curvatures approach 0 and individually. This paper presents methods for designing unreinforced boundaries of self-Airy shells, including both smooth and discrete methods. These methods work for both positively and negatively curved surfaces. The proposed methods work linearly without iteration. The preliminary results show that the seemingly very restrictive conditions admit a variety of non-trivial surfaces.
{"title":"Designing self-Airy shells with unreinforced boundaries","authors":"Yu-Chou Chiang , Hui Wang , Xinye Li , Helmut Pottmann","doi":"10.1016/j.cad.2025.103990","DOIUrl":"10.1016/j.cad.2025.103990","url":null,"abstract":"<div><div>A self-Airy membrane shell is a special type of shell structure whose shape coincides with the shell’s Airy stress surface. It provides the convenient property that any polyhedral discretization of such a surface will automatically generate a mesh in funicular equilibrium. A self-Airy shell designed for a uniform vertical load would simply have a constant <em>isotropic</em> Gaussian curvature. However, a challenge in implementing a self-Airy shell in architecture is the lack of a design method, especially in designing unreinforced boundaries. Those are singular planar curves, where the two principal curvatures approach 0 and <span><math><mi>∞</mi></math></span> individually. This paper presents methods for designing unreinforced boundaries of self-Airy shells, including both smooth and discrete methods. These methods work for both positively and negatively curved surfaces. The proposed methods work linearly without iteration. The preliminary results show that the seemingly very restrictive conditions admit a variety of non-trivial surfaces.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"191 ","pages":"Article 103990"},"PeriodicalIF":3.1,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145290009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-10DOI: 10.1016/j.cad.2025.103977
Liang Du , Jiangbei Hu , Shengfa Wang , Yu Jiang , Na Lei , Ying He , Zhongxuan Luo
Metamaterials are a family of artificial materials that achieve unique properties by designing the shape of unit cell structures. Expanding the metamaterial unit cell library is a key focus in this field, with the aim of enhancing the design flexibility to meet multifunctional requirements across diverse physical scenarios. Recent advancements in data-driven generative techniques using deep learning have significantly sped up innovations in metamaterial design. However, existing approaches mostly focus on the geometric characteristics of unit structures without considering their topological properties explicitly, which we believe are essential for enhancing design diversity and enriching material properties. In this study, we propose a novel data-driven metamaterial design methodology that combines the denoising diffusion probabilistic model with the persistent homology technique. Our model is capable of generating high-fidelity and functionally effective unit structures. Furthermore, by incorporating topological properties derived from persistent homology into the diffusion process, our method facilitates the generation of a diversity of metamaterial unit structures with richer shapes and properties. To the best of our knowledge, this is the first approach to explicitly consider topological properties in metamaterial design. In addition, our method also supports multi-scale design applications, enabling the generation of metamaterial units that align with the desired properties to achieve the optimization objectives.
{"title":"Topo-GenMeta: Generative design of metamaterials based on diffusion model with attention to topology","authors":"Liang Du , Jiangbei Hu , Shengfa Wang , Yu Jiang , Na Lei , Ying He , Zhongxuan Luo","doi":"10.1016/j.cad.2025.103977","DOIUrl":"10.1016/j.cad.2025.103977","url":null,"abstract":"<div><div>Metamaterials are a family of artificial materials that achieve unique properties by designing the shape of unit cell structures. Expanding the metamaterial unit cell library is a key focus in this field, with the aim of enhancing the design flexibility to meet multifunctional requirements across diverse physical scenarios. Recent advancements in data-driven generative techniques using deep learning have significantly sped up innovations in metamaterial design. However, existing approaches mostly focus on the geometric characteristics of unit structures without considering their topological properties explicitly, which we believe are essential for enhancing design diversity and enriching material properties. In this study, we propose a novel data-driven metamaterial design methodology that combines the denoising diffusion probabilistic model with the persistent homology technique. Our model is capable of generating high-fidelity and functionally effective unit structures. Furthermore, by incorporating topological properties derived from persistent homology into the diffusion process, our method facilitates the generation of a diversity of metamaterial unit structures with richer shapes and properties. To the best of our knowledge, this is the first approach to explicitly consider topological properties in metamaterial design. In addition, our method also supports multi-scale design applications, enabling the generation of metamaterial units that align with the desired properties to achieve the optimization objectives.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"190 ","pages":"Article 103977"},"PeriodicalIF":3.1,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Implicit Neural Representations (INRs), characterized by neural network-encoded signed distance fields, provide a powerful means to represent complex geometries continuously and efficiently. While successful in computer vision and generative modeling, integrating INRs into computational analysis workflows, such as finite element simulations, remains underdeveloped, primarily due to the necessity of explicit geometry representations (meshes). Conventional mesh-based finite element methods (FEM) introduce computational overhead, discretization errors, and manual effort, particularly for intricate or dynamically evolving geometries. Although immersed boundary methods partially address these issues, they are susceptible to numerical artifacts from explicit boundary treatments. In this work, we propose an innovative computational framework that seamlessly combines INRs with the Shifted Boundary Method (SBM) for performing high-fidelity linear elasticity simulations without explicit geometry transformations. By directly querying the neural implicit geometry, we obtain the surrogate boundaries and distance vectors essential for SBM, effectively eliminating the intermediate meshing step. We demonstrate the efficacy and robustness of our approach through elasticity simulations on complex geometries sourced from diverse representations, including triangle soup and point cloud reconstructions (Stanford Bunny, Eiffel Tower, gyroids). Our method showcases significant computational advantages and accuracy, underscoring its potential in biomedical, geophysical, and advanced manufacturing applications, thus offering a versatile tool for geometric and physical modeling aligned with contemporary design and analysis workflows.
{"title":"Mechanics simulation with Implicit Neural Representations of complex geometries","authors":"Samundra Karki, Ming-Chen Hsu, Adarsh Krishnamurthy, Baskar Ganapathysubramanian","doi":"10.1016/j.cad.2025.103978","DOIUrl":"10.1016/j.cad.2025.103978","url":null,"abstract":"<div><div>Implicit Neural Representations (INRs), characterized by neural network-encoded signed distance fields, provide a powerful means to represent complex geometries continuously and efficiently. While successful in computer vision and generative modeling, integrating INRs into computational analysis workflows, such as finite element simulations, remains underdeveloped, primarily due to the necessity of explicit geometry representations (meshes). Conventional mesh-based finite element methods (FEM) introduce computational overhead, discretization errors, and manual effort, particularly for intricate or dynamically evolving geometries. Although immersed boundary methods partially address these issues, they are susceptible to numerical artifacts from explicit boundary treatments. In this work, we propose an innovative computational framework that seamlessly combines INRs with the Shifted Boundary Method (SBM) for performing high-fidelity linear elasticity simulations without explicit geometry transformations. By directly querying the neural implicit geometry, we obtain the surrogate boundaries and distance vectors essential for SBM, effectively eliminating the intermediate meshing step. We demonstrate the efficacy and robustness of our approach through elasticity simulations on complex geometries sourced from diverse representations, including triangle soup and point cloud reconstructions (Stanford Bunny, Eiffel Tower, gyroids). Our method showcases significant computational advantages and accuracy, underscoring its potential in biomedical, geophysical, and advanced manufacturing applications, thus offering a versatile tool for geometric and physical modeling aligned with contemporary design and analysis workflows.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"190 ","pages":"Article 103978"},"PeriodicalIF":3.1,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145321805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-10-03DOI: 10.1016/j.cad.2025.103991
Rizwan Abbas , Hua Gao , Xi Li
Text-to-motion generation has made significant progress in recent years. However, existing approaches struggle to generate high-quality 3D human motions that effectively capture pose estimation. These limitations are due to weak pose estimation and limited skeletal modeling. To address these limitations, we propose DT3DPE (Dual-Transformer for 3D Pose Estimation), a framework that integrates pose estimation to generate text-aligned, realistic 3D human motions. The proposed approach introduces residual vector quantization with additional layers for encoding pose tokens, enabling the capture of fine-grained details in body dynamics. Furthermore, DT3DPE employs a dual-transformer architecture, consisting of a masked transformer for motion token prediction and a residual transformer for refining motion details. This dual-transformer architecture allows the model to generate high-fidelity 3D human poses with precise body joint positioning and smooth temporal transitions. The experimental results on HumanML3D and KIT-ML datasets demonstrate that DT3DPE outperforms existing state-of-the-art methods in text-driven 3D human motion generation. Our code is available at https://github.com/swerizwan/DT3DPE.
{"title":"Text-driven 3D human motion generation for pose estimation using dual-transformer architecture","authors":"Rizwan Abbas , Hua Gao , Xi Li","doi":"10.1016/j.cad.2025.103991","DOIUrl":"10.1016/j.cad.2025.103991","url":null,"abstract":"<div><div>Text-to-motion generation has made significant progress in recent years. However, existing approaches struggle to generate high-quality 3D human motions that effectively capture pose estimation. These limitations are due to weak pose estimation and limited skeletal modeling. To address these limitations, we propose DT3DPE (Dual-Transformer for 3D Pose Estimation), a framework that integrates pose estimation to generate text-aligned, realistic 3D human motions. The proposed approach introduces residual vector quantization with additional layers for encoding pose tokens, enabling the capture of fine-grained details in body dynamics. Furthermore, DT3DPE employs a dual-transformer architecture, consisting of a masked transformer for motion token prediction and a residual transformer for refining motion details. This dual-transformer architecture allows the model to generate high-fidelity 3D human poses with precise body joint positioning and smooth temporal transitions. The experimental results on HumanML3D and KIT-ML datasets demonstrate that DT3DPE outperforms existing state-of-the-art methods in text-driven 3D human motion generation. Our code is available at <span><span>https://github.com/swerizwan/DT3DPE</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"190 ","pages":"Article 103991"},"PeriodicalIF":3.1,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-29DOI: 10.1016/j.cad.2025.103973
Jinsong Zhang , Xiongzheng Li , Hailong Jia , Jin Li , Zhuo Su , Guidong Wang , Kun Li
Avatar reconstruction from monocular videos plays a pivotal role in various virtual and augmented reality applications. Recent methods have utilized 3D Gaussian Splatting (GS) to model human avatars, achieving fast rendering speeds with high visual quality. However, due to the independent nature of GS primitives, existing approaches often struggle to capture high-fidelity details and lack the ability to edit the reconstructed avatars effectively. To address these limitations, we propose Local Gaussian Splatting Avatar (LoGAvatar), a novel framework designed to enhance both geometry and texture modeling of human avatars. Specifically, we introduce a hierarchical Gaussian splatting framework, where local GS primitives are predicted based on sampled points from a human template model, such as SMPL. For texture modeling, we design a convolution-based texture atlas that preserves spatial continuity and enriches fine details. By aggregating local information for both geometry and texture, our approach reconstructs high-fidelity avatars while maintaining real-time rendering efficiency. Experimental results on two public datasets demonstrate the superior performance of our method in terms of avatar fidelity and rendering quality. Moreover, based on our LoGAvatar, we can edit the shape and texture of the reconstructed avatar, which inspires more customized avatar applications. The code is available at http://cic.tju.edu.cn/faculty/likun/projects/LoGAvatar.
{"title":"LoGAvatar: Local Gaussian Splatting for human avatar modeling from monocular video","authors":"Jinsong Zhang , Xiongzheng Li , Hailong Jia , Jin Li , Zhuo Su , Guidong Wang , Kun Li","doi":"10.1016/j.cad.2025.103973","DOIUrl":"10.1016/j.cad.2025.103973","url":null,"abstract":"<div><div>Avatar reconstruction from monocular videos plays a pivotal role in various virtual and augmented reality applications. Recent methods have utilized 3D Gaussian Splatting (GS) to model human avatars, achieving fast rendering speeds with high visual quality. However, due to the independent nature of GS primitives, existing approaches often struggle to capture high-fidelity details and lack the ability to edit the reconstructed avatars effectively. To address these limitations, we propose Local Gaussian Splatting Avatar (LoGAvatar), a novel framework designed to enhance both geometry and texture modeling of human avatars. Specifically, we introduce a hierarchical Gaussian splatting framework, where local GS primitives are predicted based on sampled points from a human template model, such as SMPL. For texture modeling, we design a convolution-based texture atlas that preserves spatial continuity and enriches fine details. By aggregating local information for both geometry and texture, our approach reconstructs high-fidelity avatars while maintaining real-time rendering efficiency. Experimental results on two public datasets demonstrate the superior performance of our method in terms of avatar fidelity and rendering quality. Moreover, based on our LoGAvatar, we can edit the shape and texture of the reconstructed avatar, which inspires more customized avatar applications. The code is available at <span><span>http://cic.tju.edu.cn/faculty/likun/projects/LoGAvatar</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"190 ","pages":"Article 103973"},"PeriodicalIF":3.1,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-29DOI: 10.1016/j.cad.2025.103969
Qing Pan , Yunqing Huang , Chong Chen , Xiaofeng Yang , Yongjie Jessica Zhang
In this work, we aim to numerically solve the phase-field crystal (PFC) model to simulate atomic growth on manifolds. The geometric complexity, pronounced curvature variations, and nonlinearities inherent in the physical model pose significant challenges, necessitating the development of efficient and robust numerical schemes that can handle strong coupling and nonlinear terms while accurately accounting for curved geometries. To address these challenges, we first adopt a subdivision-based isogeometric analysis (IGA) for spatial discretization. This approach effectively resolves geometric complexities by offering hierarchical refinability, geometric exactness, and adaptability to arbitrary topologies, while eliminating geometric errors commonly encountered in traditional finite element methods. For temporal discretization, the highly nonlinear terms in the model are addressed using the Invariant Energy Quadratization (IEQ) method, which linearizes the nonlinear terms and guarantees strict unconditional energy stability. However, the introduction of auxiliary variables in the IEQ method results in a linearly coupled system. To overcome this limitation and further enhance computational efficiency, we incorporate the Zero-Energy-Coupling (ZEC) approach, ultimately constructing a scheme that achieves second-order accuracy, linearity, unconditional energy stability, and a fully decoupled structure. We rigorously prove the energy stability and solvability of the proposed scheme and validate its accuracy and robustness through extensive numerical experiments conducted on manifolds, demonstrating its capability to handle intricate geometric structures and nonlinear dynamics effectively.
{"title":"Fully discrete subdivision-based IGA scheme with decoupled structure and unconditional energy stability for the phase-field crystal model on surfaces","authors":"Qing Pan , Yunqing Huang , Chong Chen , Xiaofeng Yang , Yongjie Jessica Zhang","doi":"10.1016/j.cad.2025.103969","DOIUrl":"10.1016/j.cad.2025.103969","url":null,"abstract":"<div><div>In this work, we aim to numerically solve the phase-field crystal (PFC) model to simulate atomic growth on manifolds. The geometric complexity, pronounced curvature variations, and nonlinearities inherent in the physical model pose significant challenges, necessitating the development of efficient and robust numerical schemes that can handle strong coupling and nonlinear terms while accurately accounting for curved geometries. To address these challenges, we first adopt a subdivision-based isogeometric analysis (IGA) for spatial discretization. This approach effectively resolves geometric complexities by offering hierarchical refinability, geometric exactness, and adaptability to arbitrary topologies, while eliminating geometric errors commonly encountered in traditional finite element methods. For temporal discretization, the highly nonlinear terms in the model are addressed using the Invariant Energy Quadratization (IEQ) method, which linearizes the nonlinear terms and guarantees strict unconditional energy stability. However, the introduction of auxiliary variables in the IEQ method results in a linearly coupled system. To overcome this limitation and further enhance computational efficiency, we incorporate the Zero-Energy-Coupling (ZEC) approach, ultimately constructing a scheme that achieves second-order accuracy, linearity, unconditional energy stability, and a fully decoupled structure. We rigorously prove the energy stability and solvability of the proposed scheme and validate its accuracy and robustness through extensive numerical experiments conducted on manifolds, demonstrating its capability to handle intricate geometric structures and nonlinear dynamics effectively.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"190 ","pages":"Article 103969"},"PeriodicalIF":3.1,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-26DOI: 10.1016/j.cad.2025.103979
Shoichi Tsuchie
This paper proposes a novel measure based on curvature variation to evaluate the fairness of curves. It is demonstrated that, in the simplest case, controlling the curvature using the proposed measure results in the log-aesthetic curve (LAC). In other words, by utilizing the proposed measure as a novel shape parameter, a unified framework can be established for aesthetic curves that accommodates a broader range of curvature variations, encompassing the LAC as a special case. Several examples are presented to illustrate curve evaluation using the proposed measure, along with its application to the approximation of aesthetic curves. The findings of this study offer a new perspective for understanding and evaluating the geometric properties of curves, with potential applications in curve design, analysis, and fairing.
{"title":"A new measure of fairness for curves","authors":"Shoichi Tsuchie","doi":"10.1016/j.cad.2025.103979","DOIUrl":"10.1016/j.cad.2025.103979","url":null,"abstract":"<div><div>This paper proposes a novel measure based on curvature variation to evaluate the fairness of curves. It is demonstrated that, in the simplest case, controlling the curvature using the proposed measure results in the log-aesthetic curve (LAC). In other words, by utilizing the proposed measure as a novel shape parameter, a unified framework can be established for aesthetic curves that accommodates a broader range of curvature variations, encompassing the LAC as a special case. Several examples are presented to illustrate curve evaluation using the proposed measure, along with its application to the approximation of aesthetic curves. The findings of this study offer a new perspective for understanding and evaluating the geometric properties of curves, with potential applications in curve design, analysis, and fairing.</div></div>","PeriodicalId":50632,"journal":{"name":"Computer-Aided Design","volume":"190 ","pages":"Article 103979"},"PeriodicalIF":3.1,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号