Computers & Graphics-Uk最新文献_第10页

Efficient roof reconstruction from a single aerial image 从单个航拍图像高效重建屋顶

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-13 DOI: 10.1016/j.cag.2025.104355

Yu Du , Mingyang Zhao , Jian Shi , Lubin Fan , Dong-Ming Yan

引用次数: 0

DM-SegNet: Dual-Mamba architecture for 3D medical image segmentation with global context modeling DM-SegNet：用于具有全局上下文建模的3D医学图像分割的双曼巴架构

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-13 DOI: 10.1016/j.cag.2025.104334

Chengzhang Zhu , Hangyu Ji , Hanzhen Liu , Shuhan Tang , Xiaokuan Kang , Yalong Xiao

{"title":"DM-SegNet: Dual-Mamba architecture for 3D medical image segmentation with global context modeling","authors":"Chengzhang Zhu , Hangyu Ji , Hanzhen Liu , Shuhan Tang , Xiaokuan Kang , Yalong Xiao","doi":"10.1016/j.cag.2025.104334","DOIUrl":"10.1016/j.cag.2025.104334","url":null,"abstract":"<div><div>Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence modeling, existing medical SSMs suffer from encoder–decoder incompatibility: the encoder’s 1D sequence flattening compromises spatial structures, while conventional decoders fail to leverage Mamba’s state propagation. We present DM-SegNet, a Dual-Mamba architecture integrating directional state transitions with anatomy-aware hierarchical decoding. The core innovations include a quadri-directional spatial Mamba module employing four-directional 3D scanning to maintain anatomical spatial coherence, a gated spatial convolution layer that enhances spatially sensitive feature representation prior to state modeling, and a Mamba-driven decoding framework enabling bidirectional state synchronization across scales. Extensive evaluation on two clinically significant benchmarks demonstrates the efficacy of DM-SegNet: achieving state-of-the-art Dice Similarity Coefficient (DSC) of 85.44% on the Synapse dataset for abdominal organ segmentation and 90.22% on the BraTS2023 dataset for brain tumor segmentation.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104334"},"PeriodicalIF":2.8,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144860264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multimodal Conditional 3D Face Geometry Generation 多模态条件3D面部几何生成

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-13 DOI: 10.1016/j.cag.2025.104325

Christopher Otto , Prashanth Chandran , Sebastian Weiss , Markus Gross , Gaspard Zoss , Derek Bradley

引用次数: 0

Semi-implicit representation of discrete black oil reservoir models 离散黑色油藏模型的半隐式表示

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-11 DOI: 10.1016/j.cag.2025.104373

Gisele Holtz , Waldemar Celes , Luiz Fernando Martha

{"title":"Semi-implicit representation of discrete black oil reservoir models","authors":"Gisele Holtz , Waldemar Celes , Luiz Fernando Martha","doi":"10.1016/j.cag.2025.104373","DOIUrl":"10.1016/j.cag.2025.104373","url":null,"abstract":"<div><div>Numerical black oil reservoir simulation is widely employed in the oil and gas industry for planning and predicting field explorations. Reservoir simulation relies on a topologically structured grid of hexahedral cells, modeling complex geological features. Visualization of these large-scale simulated discrete models is essential for inspection and analysis but presents challenges due to their size and geometric complexity. While conventional methods focus on rendering external faces, advanced techniques, like volume rendering, require full model representation on the GPU and an efficient point-location algorithm. Previous works proposed GPU-based model representations, but real-time applications remain limited by performance. Simplified alternatives improve speed but at the cost of accuracy. This work introduces a compact semi-implicit representation of discrete reservoir models that combines a topological coordinate field and a depth map to enable the implementation of fast and accurate visualization algorithms. Computational experiments demonstrate the advantage of the proposed representation regarding memory usage and performance while preserving the visual quality of rendered images.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104373"},"PeriodicalIF":2.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Geodesic heatmap-based segmentation-free framework for robust tooth landmark detection 基于测地热图的无分割框架鲁棒牙齿标记检测

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-11 DOI: 10.1016/j.cag.2025.104332

Weijie Liu, Shaojie Zhuang, Yeying Fan, Guangshun Wei, Yuanfeng Zhou

{"title":"Geodesic heatmap-based segmentation-free framework for robust tooth landmark detection","authors":"Weijie Liu, Shaojie Zhuang, Yeying Fan, Guangshun Wei, Yuanfeng Zhou","doi":"10.1016/j.cag.2025.104332","DOIUrl":"10.1016/j.cag.2025.104332","url":null,"abstract":"<div><div>Automatic tooth landmark detection is a crucial component in orthodontic treatment, aiding in tooth morphology assessment, treatment planning, and oral health monitoring. However, challenges remain due to diverse landmark types, varying landmark quantities, anatomical variations, and dental abnormalities. To address these issues, this paper proposes a robust two-stage framework for precise landmark detection. In the first stage, an adaptive partitioning strategy employs a lightweight network to predict tooth centroids, which are then used to partition the dental points into localized patches, eliminating the need for precise segmentation. In the second stage, a geodesic distance-based heatmap is introduced to improve landmark detection accuracy. Furthermore, an anatomy-aware spatial augmentation strategy is proposed to simulate clinically challenging scenarios, thereby improving the model’s learning capability and its robustness, particularly in cases of abnormal teeth. Extensive experimental results on a public dataset demonstrate the superiority of our method, with significant improvements over state-of-the-art approaches.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104332"},"PeriodicalIF":2.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144851887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TSlicer: An optimal topology-based slicing algorithm for Z-monotone 3D meshes TSlicer：一种基于拓扑的z单调三维网格切片算法

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-11 DOI: 10.1016/j.cag.2025.104372

Ricardo Dutra da Silva , Henrique Romaniuk Ramalho , Rodrigo Minetto , Neri Volpato , Jorge Stolfi

{"title":"TSlicer: An optimal topology-based slicing algorithm for Z-monotone 3D meshes","authors":"Ricardo Dutra da Silva , Henrique Romaniuk Ramalho , Rodrigo Minetto , Neri Volpato , Jorge Stolfi","doi":"10.1016/j.cag.2025.104372","DOIUrl":"10.1016/j.cag.2025.104372","url":null,"abstract":"<div><div>We address a computational problem that is an essential step in computer graphics, 3D printing, and many other processes: namely, the slicing of a 3D polygonal structured mesh model (as can be extracted from an STL, OBJ, or 3MF file) by a set of parallel planes. We describe <span>TSlicer</span>, a sweep-plane algorithm that exploits the topological information provided by the mesh data structure to reduce the number of intersection tests. The output is a set of polygons on each cutting plane. The topological information allows us to produce the sides of these polygons directly in the proper sequence and orientation. Furthermore, a key optimization is proposed to a topological data structure to speed up the traversal of meshes with any Z-monotone polygons as faces. We show that <span>TSlicer</span> is optimal in the asymptotic worst-case sense, and, according to experiments, substantially faster than a previous method for slicing unstructured triangle list models, as provided by STL files. The source code and mesh models used in this study are available on GitHub.<span><span><sup>1</sup></span></span></div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104372"},"PeriodicalIF":2.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144858075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

OrthoCAD-322K: A cross-modal approach for retrieving 3D CAD models from orthographic views using a graph-based framework on a developed large-scale dataset OrthoCAD-322K：一种跨模态方法，用于在开发的大规模数据集上使用基于图形的框架从正射视图中检索3D CAD模型

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-10 DOI: 10.1016/j.cag.2025.104357

Swapnil Nagnath Mahajan , Karthik Krishna M. , Ramanathan Muthuganapathy

{"title":"OrthoCAD-322K: A cross-modal approach for retrieving 3D CAD models from orthographic views using a graph-based framework on a developed large-scale dataset","authors":"Swapnil Nagnath Mahajan , Karthik Krishna M. , Ramanathan Muthuganapathy","doi":"10.1016/j.cag.2025.104357","DOIUrl":"10.1016/j.cag.2025.104357","url":null,"abstract":"<div><div>Despite the widespread adoption of 3D CAD systems, 2D orthographic drawings remain integral to engineering workflows. However, millions of legacy drawings lack corresponding 3D models, hindering their integration into modern simulation, manufacturing, and digital twin systems. Existing methods for 2D to 3D CAD retrieval often fall short of meeting the structural precision required for engineering-grade drawings. We propose a cross-modal retrieval framework that aligns vector-based 2D DXF (Drawing Exchange Format) views with 3D CAD models using contrastive learning. Our architecture integrates a Graphormer-based encoder for 2D input and a PointNet-based encoder for 3D CAD models. We introduce a novel proximity-based spatial encoding to enhance structural precision and robustness across varying view configurations. Using the filtered subset (<span><math><mo>∼</mo></math></span>283K) of the newly developed large-scale dataset OrthoCAD-322K, extensive ablation and comparison studies demonstrate the robustness and generalization of the model in different input conditions and architectures. Source code is available at <span><span>https://github.com/Swapnil-Mahajan-MS/OrthoCAD-322K</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104357"},"PeriodicalIF":2.8,"publicationDate":"2025-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144842131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CausalPrism: A visual analytics approach for subgroup-based causal heterogeneity exploration CausalPrism：一种基于子组的因果异质性探索的可视化分析方法

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-09 DOI: 10.1016/j.cag.2025.104356

Xingyu Liu , Jiehui Zhou , Xumeng Wang , Kam-Kwai Wong , Wei Zhang , Juntian Zhang , Minfeng Zhu , Wei Chen

{"title":"CausalPrism: A visual analytics approach for subgroup-based causal heterogeneity exploration","authors":"Xingyu Liu , Jiehui Zhou , Xumeng Wang , Kam-Kwai Wong , Wei Zhang , Juntian Zhang , Minfeng Zhu , Wei Chen","doi":"10.1016/j.cag.2025.104356","DOIUrl":"10.1016/j.cag.2025.104356","url":null,"abstract":"<div><div>In causal inference, estimating Heterogeneous Treatment Effects (HTEs) from observational data is critical for understanding how different subgroups respond to treatments, with broad applications such as precision medicine and targeted advertising. However, existing work on HTE, subgroup discovery, and causal visualization is insufficient to address two challenges: first, the sheer number of potential subgroups and the necessity to balance multiple objectives (<em>e.g.</em>, high effects and low variances) pose a considerable analytical challenge. Second, effective subgroup analysis has to follow the analysis goal specified by users and provide causal results with verification. To this end, we propose a visual analytics approach for subgroup-based causal heterogeneity exploration. Specifically, we first formulate causal subgroup discovery as a constrained multi-objective optimization problem and adopt a heuristic genetic algorithm to learn the Pareto front of optimal subgroups described by interpretable rules. Combining with this model, we develop a prototype system, <em>CausalPrism</em>, that incorporates tabular visualization, multi-attribute rankings, and uncertainty plots to support users in interactively exploring and sorting subgroups and explaining treatment effects. Quantitative experiments validate that the proposed model can efficiently mine causal subgroups that outperform state-of-the-art HTE and subgroup discovery methods, and case studies and expert interviews demonstrate the effectiveness and usability of the system. Code is available at <span><span>OSF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"131 ","pages":"Article 104356"},"PeriodicalIF":2.8,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144830159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NovalisArch+: Efficient hybrid procedural-AIGC for high-fidelity 3D city generation NovalisArch+：用于高保真3D城市生成的高效混合程序- aigc

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-09 DOI: 10.1016/j.cag.2025.104326

Hui Chen , Yutong Fang , Chaoqun Wang , Chengju Chen , Xiao Wen , Peng Dai , Hongxin Zhang

引用次数: 0

A parameterization method for B-spline curve interpolation via supervised regression 基于监督回归的b样条曲线插值参数化方法

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-09 DOI: 10.1016/j.cag.2025.104360

Shangyi Lin, Jieqing Feng

{"title":"A parameterization method for B-spline curve interpolation via supervised regression","authors":"Shangyi Lin, Jieqing Feng","doi":"10.1016/j.cag.2025.104360","DOIUrl":"10.1016/j.cag.2025.104360","url":null,"abstract":"<div><div>Parameterization plays a crucial role in the quality of B-spline curve interpolation, but automatically selecting an appropriate method for diverse data distributions remains challenging. A recent classification-based hybrid parameterization approach addresses this issue, statistically outperforming alternative methods, but it comes with relatively high computational costs. In this work, an automatic parameterization method via supervised regression is proposed for B-spline curve interpolation. A regressor is first trained on a dataset of randomly generated data point sequences (each of length four), with optimal parameters from those given by classical methods used as labels. The regressor then estimates the optimal local parameters for each set of four consecutive data points based on their local geometric distribution. Global parameters that closely match the local ones are computed through a merging process. Since local parameters are directly generated by the regressor, the proposed method is more efficient than the classification-based hybrid approach. Additionally, since regressors are inherently more flexible than classifiers, the proposed regression-based method is compatible with any existing or new parameterization method — rather than being limited to just the three representative methods used in the classification-based approach — and is capable of producing better results. Experimental results demonstrate that the proposed method efficiently produces superior interpolation curves compared to existing techniques, even outperforming the previous classification-based approach with an idealized theoretical classifier.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104360"},"PeriodicalIF":2.8,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0