检索结果-内蒙古大学图书馆

Fast best viewpoint selection with geometry-enhanced multiple views and cross-modal distillation

VISUAL COMPUTER 2025年第7期41卷 5075-5086页

作者： Cao, Zidi Han, Jiayi Yang, Sipeng Jin, Xiaogang Zhejiang Univ State Key Lab CAD & CG Hangzhou Peoples R China Inspur Genersoft Co Ltd Inspur Grp Co Ltd Jinan Peoples R China

Best viewpoint selection (BVS) aims to automatically identify the most informative and human preference viewpoints of 3D shapes, clearly conveying their complexity and structure. Despite advancements in mesh-based BVS using multi-views, the current state-of-the-art BVS method requires 20-30 rendered views and is limited to predefined viewpoints, which may miss optimal viewpoints and is impractical in time-sensitive scenarios. To address these limitations, we present a new dual-branch fast BVS regression model that significantly reduces reliance on extensive input views, enables continuous perspective prediction, and enhances interactive response speeds. Our method incorporates a geometry-enhanced multi-view feature extractor combined with a learnable token and employs a cross-modal distillation approach to deepen understanding of 3D structures. By integrating alignment constraints between 3D geometry descriptors and multi-view expressions, our approach minimizes the need for extensive rendering views, significantly reducing computational demands. Experimental results on public benchmarks show that our method is about 35 times faster than the state-of-the-art method when only six views are adopted, while also achieving the best quantitative metrics.

关键词： Best viewpoint selection Cross-modal distillation Multiple views Viewpoint prediction

来源：评论

学校读者我要写书评

暂无评论

TOVis: a visual analytics system for outcome-driven treatment plan optimization

引用

JOURNAL OF VISUALIZATION 2025年 1-18页

作者： Liu, Huan Dai, Haoran Xu, Jin Chen, Juntian Tao, Yubo Lin, Hai Zhejiang Univ State Key Lab CAD&CG Hangzhou Peoples R China Hangzhou Normal Univ Alibaba Business Sch Hangzhou Peoples R China

Personalized medicine advocates that physicians should provide medical treatments based on patients' individual conditions. However, combining a patient's medical history and current condition to develop a customized treatment plan and evaluate its possible outcomes is time-consuming. To address this issue, various outcome prediction methods and medical decision-making systems have emerged to assist physicians in the above process. Unfortunately, they cannot well support outcome-driven treatment optimization, where physicians can iteratively optimize treatment plans according to expected outcomes, aiming to provide the best possible treatment plan for patients. Therefore, this paper proposes an interactive visual analytics system, TOVis, to support outcome-driven treatment plan optimization using a neural network model and post-analysis technology. TOVis can guide physicians to optimize treatment plans in two manners: manual adjustment based on domain knowledge and experience, and automatic adjustment under the constraints of expected outcomes. We also design a provenance tree to organize the optimization history, which enables visual comparisons of different plans to make medical decisions. Finally, quantitative evaluation, case studies, and physician interviews on an acute kidney injury dataset demonstrate the usefulness and effectiveness of TOVis in treatment planning.

关键词： Visual analytics Electronic health records Outcome prediction Treatment plan optimization

来源：评论

学校读者我要写书评

暂无评论

Dual discriminator GANs with multi-focus label matching for image-aware layout generation

引用

DISPLAYS 2025年 87卷

作者： Xu, Chenchen Han, Kaixin Zhou, Min Xu, Weiwei Anhui Normal Univ Wuhu Peoples R China Zhejiang Univ State Key Lab CAD&CG Hangzhou Peoples R China Alibaba Grp Hangzhou Peoples R China

Image-aware layout generation involves arranging graphic elements, including logo, text, underlay, and embellishment, at the appropriate position on the canvas, constituting a fundamental step in poster design. This task requires considering both the relationships among elements and the interaction between elements and images. However, existing layout generation models struggle to simultaneously satisfy explicit aesthetic principles like alignment and non-overlapping, along with implicit aesthetic principles related to the harmonious composition of images and elements. To overcome these challenges, this paper designs a GAN with dual discriminators, called DD-GAN, to generate graphic layouts according to image contents. In addition, we introduce a multi- focus label matching method to provide richer supervision and optimize model training. The incorporation of multi-focus label matching not only accelerates convergence during training but also enables the model to better capture both explicit and implicit aesthetic principles in image-aware layout generation. Quantitative and qualitative evaluations consistently demonstrate that DD-GAN, coupled with multi-focus label matching, achieves state-of-the-art performance, producing high-quality image-aware graphic layouts for advertising posters.

关键词： Image-aware layout generation Dual discriminators DD-GAN Multi-focus label matching

来源：评论

学校读者我要写书评

暂无评论

Stochastic Geometric Iterative Method for Loop Subdivision Surface Fitting

引用

COMMUNICATIONS IN MATHEMATICS AND STATISTICS 2025年第1期13卷 217-231页

作者： Xu, Chenkai He, Yaqi Hu, Hui Lin, Hongwei Zhejiang Univ Sch Math Sci Hangzhou Zhejiang Peoples R China Zhejiang Univ State Key Lab CAD &CG Hangzhou Zhejiang Peoples R China

In this paper, we propose a stochastic geometric iterative method (S-GIM) to approximate the high-resolution 3D models by finite loop subdivision surfaces. Given an input mesh as the fitting target, the initial control mesh is generated using the mesh simplification algorithm. Then, our method adjusts the control mesh iteratively to make its finite loop subdivision surface approximate the input mesh. In each geometric iteration, we randomly select part of points on the subdivision surface to calculate the difference vectors and distribute the vectors to the control points. Finally, the control points are updated by adding the weighted average of these difference vectors. We prove the convergence of S-GIM and verify it by demonstrating error curves in the experiment. In addition, compared with existing geometric iterative methods, S-GIM has a shorter running time under the same number of iteration steps.

关键词： Geometric iterative Surface fitting Subdivision surface Stochastic PIA Stochastic LSPIA

来源：评论

学校读者我要写书评

暂无评论

Hybrid mesh-neural representation for 3D transparent object reconstruction

引用

Computational Visual Media 2025年第1期11卷 123-140页

作者： Jiamin Xu Zihan Zhu Hujun Bao Weiwei Xu College of Computer Science Hangzhou Dianzi UniversityHangzhou 310018China State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310058China College of Computer Science ETH ZurichZurich 8092Switzerland.

In this study,we propose a novel method to reconstruct the 3D shapes of transparent objects using images captured by handheld cameras under natural lighting *** combines the advantages of an explicit mesh and multi-layer perceptron(MLP)network as a hybrid representation to simplify the capture settings used in recent *** obtaining an initial shape through multi-view silhouettes,we introduced surface-based local MLPs to encode the vertex displacement field(VDF)for reconstructing surface *** design of local MLPs allowed representation of the VDF in a piecewise manner using two-layer MLP networks to support the optimization *** local MLPs on the surface instead of on the volume also reduced the search *** a hybrid representation enabled us to relax the ray–pixel correspondences that represent the light path constraint to our designed ray–cell correspondences,which significantly simplified the implementation of a single-image-based environment-matting *** evaluated our representation and reconstruction algorithm on several transparent objects based on ground truth *** experimental results show that our method produces high-quality reconstructions that are superior to those of state-of-the-art methods using a simplified data-acquisition setup.

关键词： transparent object 3D reconstruction environment matting neural rendering

来源：评论

学校读者我要写书评

暂无评论

Efficient 3-D Model Machining Strategy Prediction With Topology-Spanning Aggregation and GMU Data Augmentation

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第4期21卷 3127-3136页

作者： Ren, Lei Wang, Yuqing Chen, Wei Wang, Haiteng Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Beihang Univ State Key Lab Intelligent Mfg Syst Technol Beijing 100854 Peoples R China Zhejiang Univ State Key Lab CAD&CG Hangzhou 310058 Peoples R China

During the machining process of parts, choosing appropriate machining strategies optimizes production costs effectively. However, when the amount of data is limited, existing neural networks often struggle to fit the data accurately. Meanwhile, existing neural networks suffer from information dilution and lack effective mechanisms for direct information transfer between nonadjacent surfaces. This article proposes a method to extract General Machining Unit data. This data improves few-shot training performance. We investigate the distribution and information flow within General Machining Units and design a new way of data augmentation. In addition, to address the information dilution, a novel wormhole mechanism is proposed to aggregate information that spans the topological connections. In the backbone, we propose the Brep-WH layer that integrates wormhole mechanisms and attention pool layers. Both the Brep-WH network and the General Machining Unit data successfully improve the accuracy of the milling strategy dataset and the Fusion 360 Gallery segmentation dataset.

关键词： General machining unit (GMU) machining strategy prediction wormhole mechanism

来源：评论

学校读者我要写书评

暂无评论

Toward Weather-Robust 3D Human Body Reconstruction: Millimeter-Wave Radar-Based Dataset, Benchmark, and Multi-Modal Fusion

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第1期35卷 273-286页

作者： Chen, Anjun Wang, Xiangyu Shi, Kun Huo, Yuchi Chen, Jiming Ye, Qi Coll Control Sci & Engn Hangzhou 310027 Peoples R China Zhejiang Univ State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China Zhejiang Univ State Key Lab CAD&CG Hangzhou 310027 Peoples R China

3D human reconstruction from RGB images achieves decent results in good weather conditions but degrades dramatically in rough weather. Complementarily, mmWave radars have been employed to reconstruct 3D human joints and meshes in rough weather. However, combining RGB and mmWave signals for weather-robust 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images. The limited research about the impact of missing points and sparsity features of mmWave data on reconstruction performance, as well as the lack of available datasets for paired mmWave-RGB data, further complicates the process of fusing the two modalities. To fill these gaps, we build up an automatic 3D body annotation system with multiple sensors to collect a large-scale mmWave dataset. The dataset consists of synchronized and calibrated mmWave radar point clouds and RGB(D) images under different weather conditions and skeleton/mesh annotations for humans in these scenes. With this dataset, we conduct a comprehensive analysis about the limitations of single-modality reconstruction and the impact of missing points and sparsity on the reconstruction performance. Based on the guidance of this analysis, we design ImmFusion, the first mmWave-RGB fusion solution to robustly reconstruct 3D human bodies in various weather conditions. Specifically, our ImmFusion consists of image and point backbones for token feature extraction and a Transformer module for token fusion. The image and point backbones refine global and local features from original data, and the Fusion Transformer Module aims for effective information fusion of two modalities by dynamically selecting informative tokens. Extensive experiments demonstrate that ImmFusion can efficiently utilize the information of two modalities to achieve robust 3D human body reconstruction in various weather environments. In addition, our method achieves superior accuracy compared to that of the state-of-the-

关键词： Millimeter wave communication Image reconstruction Three-dimensional displays Point cloud compression Meteorology Transformers Skeleton 3D human body reconstruction mmWave-RGB fusion human body dataset

来源：评论

学校读者我要写书评

暂无评论

Assembly simulation method based on joint optimization of initial pose and contact deformation

ROBOTIC INTELLIGENCE AND AUTOMATION

引用

ROBOTIC INTELLIGENCE AND AUTOMATION 2025年第3期45卷 356-372页

作者： Sa, Guodong Han, Yuxin Qiu, Chan Liu, Zhenyu Wang, Zhuonan Ma, Ruochen Zheng, Jun Tan, Jianrong Zhejiang Univ Ningbo Innovat Ctr Ningbo Peoples R China Zhejiang Univ State Key Lab CAD&CG Hangzhou Peoples R China Dongfang Turbine Co Ltd Deyang Peoples R China

Purpose - This paper aims to better evaluate assembly accuracy and guide the product design and manufacturing process. By simulating force, deformation, and contact during the assembly process, an assembly simulation method based on the joint optimization of initial pose and contact deformation is proposed. Design/methodology/approach - In assembly simulation, high precision skin model samples are constructed based on point cloud features extracted from real surfaces and contact deformation calculation is integrated into the initial attitude solving process to obtain assembly positioning deviations, finally product deviations accumulation is calculated by Jacobi matrix. Findings - The assembly simulation method for joint optimization of initial pose and contact deformation is suitable for solving the assembly process of nonideal parts with complex shape deviations. Considering the constraints of surface morphological features and contact deformations, a more realistic assembly position can be obtained. And the validity of the method is verified by plane assembly, which is applied in the tolerance analysis of centrifuges. Originality/value - Currently, the main approach to flexible assembly simulation uses a two-step independent strategy: first, the initial rigid contact attitude is calculated, and then the flexible deformation is calculated. However, the determination of the initial rigid assembly attitude is mainly based on geometrical features, ignoring the effect of material flexibility, which simplifies the assembly process. The assembly simulation method proposed in this paper, which simultaneously optimizes the initial contact attitude, contact area and final contact deformation, aims to provide more accurate assembly results for tolerance analysis.

关键词： Flexible assembly Skin model shapes Contact deformation Tolerance analysis

来源：评论

学校读者我要写书评

暂无评论

Robust full-layer prismatic mesh generation based on bijective mapping

引用

JOURNAL OF COMPUTATIONAL PHYSICS 2025年 524卷

作者： Ye, Hongfei Liu, Taoran Ni, Haonan Chen, Jianjun Zhejiang Univ Sch Aeronaut & Astronaut 38 Zheda Rd Hangzhou 310000 Zhejiang Peoples R China Zhejiang Univ State Key Lab CAD&CG 866 Yuhangtang Rd Hangzhou 310000 Zhejiang Peoples R China

Prismatic/tetrahedral hybrid meshes are widely used in CFD simulations involving RANS calculations. However, premature termination during Advancing Layer Method (ALM) generation often necessitates using highly distorted pyramidal elements, compromising overall mesh quality and hindering subsequent tetrahedral mesh generation. To address this, we propose a robust full-layer prismatic mesh generation scheme based on recent advances in piecewise linear bijective mapping. Our scheme iteratively deforms an initial mesh towards an orthogonal target, minimizing the bijective mapping energy via a robust, area/volume-preserving As-Rigid-As- Possible mapping method. Extending to complex geometry in 3D, we further introduce an interpolation-based prismatic mesh generation method, enabling the generation of computationally suitable meshes for complex geometries.

关键词： Prismatic mesh Anisotropy Mesh generation As-rigid-as-possible mapping Boundary layer mesh

来源：评论

学校读者我要写书评

暂无评论

Tool digital twin based on knowledge embedding for precision CNC machine tools: Wear prediction for collaborative multi-tool

引用

JOURNAL OF MANUFACTURING SYSTEMS 2025年 80卷 157-175页

作者： Sun, Jiacheng Wang, Dong Liu, Zhenyu Qiu, Chan Liu, Hui Sa, Guodong Tan, Jianrong Zhejiang Univ State Key Lab CAD & CG Hangzhou 310027 Peoples R China Zhejiang Univ Ningbo Innovat Ctr Ningbo 315100 Peoples R China Zhejiang Univ Sch Mech Engn Hangzhou 310058 Peoples R China

Tool wear prediction is vital for enhancing machining accuracy and ensuring production safety. However, challenges arise from non-processing data interference and missing tool wear samples, complicating the construction of accurate prediction models. Additionally, the complexity of collaborative multi-tool operations on precision computer numerical control (CNC) machine tools, where varying tool types and complex working conditions exist, further exacerbates the difficulty of achieving precise wear prediction. To address these challenges, this paper introduces a digital twin architecture for tool wear prediction, based on knowledge embedding. The proposed architecture is designed to predict the wear of multiple tools, incorporating modules for processing data screening, missing value completion, wear state classification, and so on. On the basis of obtaining high- quality sensing data and complete tool wear values, the wear state and machining process knowledge are embedded into the prediction process. A tool wear prediction model is then constructed based on a KolmogorovArnold integrated time convolutional network (KA-TCN), so as to achieve accurate prediction of multi-tool wear. The effectiveness of the method is validated using data from two grinding wheel wear test platforms and two milling datasets, PHM2010 and NASA. Experimental results demonstrate that the knowledge embedded KA-TCN model outperforms existing approaches, improving prediction accuracy by over 22.4 % on the milling dataset, and by 76.4 % in grinding wheel wear prediction compared to classical methods.

关键词： Digital twin Tool wear prediction Knowledge embedding Cooperative multi-tool CNC machine tools

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：