We propose a suite of strategies for the parallel solution of fully implicit monolithic fluid-structure interaction(FSI).The solver is based on a modeling approach that uses the velocity and pressure as the primitive ...We propose a suite of strategies for the parallel solution of fully implicit monolithic fluid-structure interaction(FSI).The solver is based on a modeling approach that uses the velocity and pressure as the primitive variables,which offers a bridge between computational fluid dynamics(CFD)and computational structural dynamics.The spatiotemporal discretization leverages the variational multiscale formulation and the generalized-αmethod as a means of providing a robust discrete scheme.In particular,the time integration scheme does not suffer from the overshoot phenomenon and optimally dissipates high-frequency spurious modes in both subproblems of FSI.Based on the chosen fully implicit scheme,we systematically develop a combined suite of nonlinear and linear solver strategies.Invoking a block factorization of the Jacobian matrix,the Newton-Raphson procedure is reduced to solving two smaller linear systems in the multi-corrector stage.The first is of the elliptic type,indicating that the algebraic multigrid method serves as a well-suited option.The second exhibits a two-by-two block structure that is analogous to the system arising in CFD.Inspired by prior studies,the additive Schwarz domain decomposition method and the block-factorization-based preconditioners are invoked to address the linear problem.Since the number of unknowns matches in both subdomains,it is straightforward to balance loads when parallelizing the algorithm for distributed-memory architectures.We use two representative FSI benchmarks to demonstrate the robustness,efficiency,and scalability of the overall FSI solver framework.In particular,it is found that the developed FSI solver is comparable to the CFD solver in several aspects,including fixed-size and isogranular scalability as well as robustness.展开更多
Realistic human reconstruction embraces an extensive range of applications as depth sensors advance.However,current stateof-the-art methods with RGB-D input still suffer from artefacts,such as noisy surfaces,non-human...Realistic human reconstruction embraces an extensive range of applications as depth sensors advance.However,current stateof-the-art methods with RGB-D input still suffer from artefacts,such as noisy surfaces,non-human shapes,and depth ambiguity,especially for the invisible parts.The authors observe the main issue is the lack of geometric semantics without using depth input priors fully.This paper focuses on improving the representation ability of implicit function,exploring an effective method to utilise depth-related semantics effectively and efficiently.The proposed geometry-enhanced implicit function enhances the geometric semantics with the extra voxel-aligned features from point clouds,promoting the completion of missing parts for unseen regions while preserving the local details on the input.For incorporating multi-scale pixel-aligned and voxelaligned features,the authors use the Squeeze-and-Excitation attention to capture and fully use channel interdependencies.For the multi-view reconstruction,the proposed depth-enhanced attention explicitly excites the network to“sense”the geometric structure for a more reasonable feature aggregation.Experiments and results show that our method outperforms current RGB and depth-based SOTA methods on the challenging data from Twindom and Thuman3.0,and achieves a detailed and completed human reconstruction,balancing performance and efficiency well.展开更多
The accuracy of numerical computation heavily relies on appropriate meshing,whichserves as the foundation for numerical computation.Although adaptive refinement methods areavailable,an adaptive numerical solution is l...The accuracy of numerical computation heavily relies on appropriate meshing,whichserves as the foundation for numerical computation.Although adaptive refinement methods areavailable,an adaptive numerical solution is likely to be ineffective if it originates from a poorly ini-tial mesh.Therefore,it is crucial to generate meshes that accurately capture the geometric features.As an indispensable input in meshing methods,the Mesh Size Function(MSF)determines the qual-ity of the generated mesh.However,the current generation of MSF involves human participation tospecify numerous parameters,leading to difficulties in practical usage.Considering the capacity ofmachine learning to reveal the latent relationships within data,this paper proposes a novel machinelearning method,Implicit Geometry Neural Network(IGNN),for automatic prediction of appro-priate MSFs based on the existing mesh data,enabling the generation of unstructured meshes thatalign precisely with geometric features.IGNN employs the generative adversarial theory to learnthe mapping between the implicit representation of the geometry(Signed Distance Function,SDF)and the corresponding MSF.Experimental results show that the proposed method is capableof automatically generating appropriate meshes and achieving comparable meshing results com-pared to traditional methods.This paper demonstrates the possibility of significantly decreasingthe workload of mesh generation using machine learning techniques,and it is expected to increasethe automation level of mesh generation.展开更多
Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world appli...Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world applications.Few-shot object detection presents a new research idea that aims to localize and classify objects in images using only limited annotated examples.However,the inherent challenge in few-shot object detection lies in the insufficient sample diversity to fully characterize the sample feature distribution,which consequently impacts model performance.Inspired by contrastive learning principles,we propose an Implicit Feature Contrastive Learning(IFCL)module to address this limitation and augment feature diversity for more robust representational learning.This module generates augmented support sample features in a mixed feature space and implicitly contrasts them with query Region of Interest(RoI)features.This approach facilitates more comprehensive learning of both intra-class feature similarity and inter-class feature diversity,thereby enhancing the model’s object classification and localization capabilities.Extensive experiments on PASCAL VOC show that our method achieves a respective improvement of 3.2%,1.8%,and 2.3%on 10-shot of three Novel Sets compared to the baseline model FPD.展开更多
基金This work was supported by the National Natural Science Foundation of China(Grant No.12172160)Shenzhen Science and Technology Program(Grant No.JCYJ20220818100600002)+1 种基金South-ern University of Science and Technology(Grant No.Y01326127)the Department of Science and Technology of Guangdong Province(Grant Nos.2020B1212030001 and 2021QN020642).
文摘We propose a suite of strategies for the parallel solution of fully implicit monolithic fluid-structure interaction(FSI).The solver is based on a modeling approach that uses the velocity and pressure as the primitive variables,which offers a bridge between computational fluid dynamics(CFD)and computational structural dynamics.The spatiotemporal discretization leverages the variational multiscale formulation and the generalized-αmethod as a means of providing a robust discrete scheme.In particular,the time integration scheme does not suffer from the overshoot phenomenon and optimally dissipates high-frequency spurious modes in both subproblems of FSI.Based on the chosen fully implicit scheme,we systematically develop a combined suite of nonlinear and linear solver strategies.Invoking a block factorization of the Jacobian matrix,the Newton-Raphson procedure is reduced to solving two smaller linear systems in the multi-corrector stage.The first is of the elliptic type,indicating that the algebraic multigrid method serves as a well-suited option.The second exhibits a two-by-two block structure that is analogous to the system arising in CFD.Inspired by prior studies,the additive Schwarz domain decomposition method and the block-factorization-based preconditioners are invoked to address the linear problem.Since the number of unknowns matches in both subdomains,it is straightforward to balance loads when parallelizing the algorithm for distributed-memory architectures.We use two representative FSI benchmarks to demonstrate the robustness,efficiency,and scalability of the overall FSI solver framework.In particular,it is found that the developed FSI solver is comparable to the CFD solver in several aspects,including fixed-size and isogranular scalability as well as robustness.
基金supported by the National Key R&D Programme of China(2022YFF0902200).
文摘Realistic human reconstruction embraces an extensive range of applications as depth sensors advance.However,current stateof-the-art methods with RGB-D input still suffer from artefacts,such as noisy surfaces,non-human shapes,and depth ambiguity,especially for the invisible parts.The authors observe the main issue is the lack of geometric semantics without using depth input priors fully.This paper focuses on improving the representation ability of implicit function,exploring an effective method to utilise depth-related semantics effectively and efficiently.The proposed geometry-enhanced implicit function enhances the geometric semantics with the extra voxel-aligned features from point clouds,promoting the completion of missing parts for unseen regions while preserving the local details on the input.For incorporating multi-scale pixel-aligned and voxelaligned features,the authors use the Squeeze-and-Excitation attention to capture and fully use channel interdependencies.For the multi-view reconstruction,the proposed depth-enhanced attention explicitly excites the network to“sense”the geometric structure for a more reasonable feature aggregation.Experiments and results show that our method outperforms current RGB and depth-based SOTA methods on the challenging data from Twindom and Thuman3.0,and achieves a detailed and completed human reconstruction,balancing performance and efficiency well.
基金co-supported by the Aeronautical Science Foundation of China(Nos.2018ZA52002 and 2019ZA052011)。
文摘The accuracy of numerical computation heavily relies on appropriate meshing,whichserves as the foundation for numerical computation.Although adaptive refinement methods areavailable,an adaptive numerical solution is likely to be ineffective if it originates from a poorly ini-tial mesh.Therefore,it is crucial to generate meshes that accurately capture the geometric features.As an indispensable input in meshing methods,the Mesh Size Function(MSF)determines the qual-ity of the generated mesh.However,the current generation of MSF involves human participation tospecify numerous parameters,leading to difficulties in practical usage.Considering the capacity ofmachine learning to reveal the latent relationships within data,this paper proposes a novel machinelearning method,Implicit Geometry Neural Network(IGNN),for automatic prediction of appro-priate MSFs based on the existing mesh data,enabling the generation of unstructured meshes thatalign precisely with geometric features.IGNN employs the generative adversarial theory to learnthe mapping between the implicit representation of the geometry(Signed Distance Function,SDF)and the corresponding MSF.Experimental results show that the proposed method is capableof automatically generating appropriate meshes and achieving comparable meshing results com-pared to traditional methods.This paper demonstrates the possibility of significantly decreasingthe workload of mesh generation using machine learning techniques,and it is expected to increasethe automation level of mesh generation.
基金funded by the China Chongqing Municipal Science and Technology Bureau,grant numbers CSTB2024TIAD-CYKJCXX0009,CSTB2024NSCQ-LZX0043,CSTB2022NSCQ-MSX0288Chongqing Municipal Commission of Housing and Urban-Rural Development,grant number CKZ2024-87+3 种基金the Chongqing University of Technology Graduate Education High-Quality Development Project,grant number gzlsz202401the Chongqing University of Technology—Chongqing LINGLUE Technology Co.,Ltd.Electronic Information(Artificial Intelligence)Graduate Joint Training Basethe Postgraduate Education and Teaching Reform Research Project in Chongqing,grant number yjg213116the Chongqing University of Technology-CISDI Chongqing Information Technology Co.,Ltd.Computer Technology Graduate Joint Training Base.
文摘Although conventional object detection methods achieve high accuracy through extensively annotated datasets,acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world applications.Few-shot object detection presents a new research idea that aims to localize and classify objects in images using only limited annotated examples.However,the inherent challenge in few-shot object detection lies in the insufficient sample diversity to fully characterize the sample feature distribution,which consequently impacts model performance.Inspired by contrastive learning principles,we propose an Implicit Feature Contrastive Learning(IFCL)module to address this limitation and augment feature diversity for more robust representational learning.This module generates augmented support sample features in a mixed feature space and implicitly contrasts them with query Region of Interest(RoI)features.This approach facilitates more comprehensive learning of both intra-class feature similarity and inter-class feature diversity,thereby enhancing the model’s object classification and localization capabilities.Extensive experiments on PASCAL VOC show that our method achieves a respective improvement of 3.2%,1.8%,and 2.3%on 10-shot of three Novel Sets compared to the baseline model FPD.
