Computer Graphics Forum最新文献_第3页

LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images LucidFusion：重建三维高斯任意未置图像

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70227

Hao He, Yixun Liang, Luozhou Wang, Yuanhao Cai, Xinli Xu, Haoxiang Guo, Xiang Wen, Yingcong Chen

引用次数: 0

FAHNet: Accurate and Robust Normal Estimation for Point Clouds via Frequency-Aware Hierarchical Geometry 基于频率感知层次几何的点云准确鲁棒正态估计

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70264

Chengwei Wang, Wenming Wu, Yue Fei, Gaofeng Zhang, Liping Zheng

{"title":"FAHNet: Accurate and Robust Normal Estimation for Point Clouds via Frequency-Aware Hierarchical Geometry","authors":"Chengwei Wang, Wenming Wu, Yue Fei, Gaofeng Zhang, Liping Zheng","doi":"10.1111/cgf.70264","DOIUrl":"https://doi.org/10.1111/cgf.70264","url":null,"abstract":"Point cloud normal estimation underpins many 3D vision and graphics applications. Precise normal estimation in regions of sharp curvature and high-frequency variation remains a major bottleneck; existing learning-based methods still struggle to isolate fine geometry details under noise and uneven sampling. We present FAHNet, a novel frequency-aware hierarchical network that precisely tackles those challenges. Our Frequency-Aware Hierarchical Geometry (FAHG) feature extraction module selectively amplifies and merges cross-scale cues, ensuring that both fine-grained local features and sharp structures are faithfully represented. Crucially, a dedicated Frequency-Aware geometry enhancement (FA) branch intensifies sensitivity to abrupt normal transitions and sharp features, preventing the common over-smoothing limitation. Extensive experiments on synthetic benchmarks (PCPNet, FamousShape) and real-world scans (SceneNN) demonstrate that FAHNet outperforms state-of-the-art approaches in normal estimation accuracy. Ablation studies further quantify the contribution of each component, and downstream surface reconstruction results validate the practical impact of our design.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 7","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145297126","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

Uncertainty-Aware Adjustment via Learnable Coefficients for Detailed 3D Reconstruction of Clothed Humans from Single Images 基于可学习系数的不确定性感知调整在单幅图像中对穿衣服的人进行详细的三维重建

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70239

Yadan Yang, Yunze Li, Fangli Ying, Aniwat Phaphuangwittayakul, Riyad Dhuny

{"title":"Uncertainty-Aware Adjustment via Learnable Coefficients for Detailed 3D Reconstruction of Clothed Humans from Single Images","authors":"Yadan Yang, Yunze Li, Fangli Ying, Aniwat Phaphuangwittayakul, Riyad Dhuny","doi":"10.1111/cgf.70239","DOIUrl":"https://doi.org/10.1111/cgf.70239","url":null,"abstract":"Although single-image 3D human reconstruction has made significant progress in recent years, few of the current state-of-the-art methods can accurately restore the appearance and geometric details of loose clothing. To achieve high-quality reconstruction of a human body wearing loose clothing, we propose a learnable dynamic adjustment framework that integrates side-view features and the uncertainty of the parametric human body model to adaptively regulate its reliability based on the clothing type. Specifically, we first adopt the Vision Transformer model as an encoder to capture the image features of the input image, and then employ SMPL-X to decouple the side-view body features. Secondly, to reduce the limitations imposed by the regularization of the parametric model, particularly for loose garments, we introduce a learnable coefficient to reduce the reliance on SMPL-X. This strategy effectively accommodates the large deformations caused by loose clothing, thereby accurately expressing the posture and clothing in the image. To evaluate the effectiveness, we validate our method on the public CLOTH4D and Cape datasets, and the experimental results demonstrate better performance compared to existing approaches. The code is available at https://github.com/yyd0613/CoRe-Human.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 7","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145297322","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

Gaussian Splatting for Large-Scale Aerial Scene Reconstruction From Ultra-High-Resolution Images 高斯溅射用于超高分辨率图像的大规模航拍场景重建

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70265

Qiulin Sun, Wei Lai, Yixian Li, Yanci Zhang

{"title":"Gaussian Splatting for Large-Scale Aerial Scene Reconstruction From Ultra-High-Resolution Images","authors":"Qiulin Sun, Wei Lai, Yixian Li, Yanci Zhang","doi":"10.1111/cgf.70265","DOIUrl":"https://doi.org/10.1111/cgf.70265","url":null,"abstract":"Using 3D Gaussian splatting to reconstruct large-scale aerial scenes from ultra-high-resolution images is still a challenge problem because of two memory bottlenecks - excessive Gaussian primitives and the tensor sizes for ultra-high-resolution images. In this paper, we propose a task partitioning algorithm that operates in both object and image space to generate a set of small-scale subtasks. Each subtask's memory footprints is strictly limited, enabling training on a single high-end consumer-grade GPU. More specifically, Gaussian primitives are clustered into blocks in object space, and the input images are partitioned into sub-images according to the projected footprints of these blocks. This dual-space partitioning significantly reduces training memory requirements. During subtask training, we propose a depth comparison method to generate a mask map for each sub-image. This mask map isolates pixels primarily contributed by the Gaussian primitives of the current subtask, excluding all other pixels from training. Experimental results demonstrate that our method successfully achieves large-scale aerial scene reconstruction using 9K resolution images on a single RTX 4090 GPU. The novel views synthesized by our method retain significantly more details than those from current state-of-the-art methods.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 7","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145297351","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

Self-Supervised Humidity-Controllable Garment Simulation via Capillary Bridge Modeling 基于毛细管桥模型的自监督湿度控制服装仿真

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70236

M. Shi, X. Wang, J. Zhang, L. Gao, D. Zhu, H. Zhang

{"title":"Self-Supervised Humidity-Controllable Garment Simulation via Capillary Bridge Modeling","authors":"M. Shi, X. Wang, J. Zhang, L. Gao, D. Zhu, H. Zhang","doi":"10.1111/cgf.70236","DOIUrl":"https://doi.org/10.1111/cgf.70236","url":null,"abstract":"Simulating wet clothing remains a significant challenge due to the complex physical interactions between moist fabric and the human body, compounded by the lack of dedicated datasets for training data-driven models. Existing self-supervised approaches struggle to capture moisture-induced dynamics such as skin adhesion, anisotropic surface resistance, and non-linear wrinkling, leading to limited accuracy and efficiency. To address this, we present SHGS, a novel self-supervised framework for humidity-controllable clothing simulation grounded in the physical modeling of capillary bridges that form between fabric and skin. We abstract the forces induced by wetness into two physically motivated components: a normal adhesive force derived from Laplace pressure and a tangential shear-resistance force that opposes relative motion along the fabric surface. By formulating these forces as potential energy for conservative effects and as mechanical work for non-conservative effects, we construct a physics-consistent wetness loss. This enables self-supervised training without requiring labeled data of wet clothing. Our humidity-sensitive dynamics are driven by a multi-layer graph neural network, which facilitates a smooth and physically realistic transition between different moisture levels. This architecture decouples the garment's dynamics in wet and dry states through a local weight interpolation mechanism, adjusting the fabric's behavior in response to varying humidity conditions. Experiments demonstrate that SHGS outperforms existing methods in both visual fidelity and computational efficiency, marking a significant advancement in realistic wet-cloth simulation.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 7","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145297028","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

FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models 平面CAD: CAD模型神经sdf的快速曲率正则化

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70249

Haotian Yin, Aleksander Plocharski, Michal Jan Wlodarczyk, Mikolaj Kida, Przemyslaw Musialski

引用次数: 0

Region-Aware Sparse Attention Network for Lane Detection 基于区域感知的稀疏注意网络的车道检测

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70246

Yan Deng, Guoqiang Xiao

{"title":"Region-Aware Sparse Attention Network for Lane Detection","authors":"Yan Deng, Guoqiang Xiao","doi":"10.1111/cgf.70246","DOIUrl":"https://doi.org/10.1111/cgf.70246","url":null,"abstract":"Lane detection is a fundamental task in intelligent driving systems. However, the slender and sparse structure of lanes, combined with the dominance of irrelevant background regions in road scenes, makes accurate lane localization particularly challenging, especially under complex and adverse conditions. To address these issues, we propose a novel Region-Aware Sparse Attention Network (RSANet), which is designed to selectively enhance lane-relevant features while suppressing background interference. Specifically, we introduce the Region-guided Pooling Predictor (RPP) that generates lane region activation maps to guide the backbone network in focusing on informative areas. To improve the multi-scale feature fusion capability of the Feature Pyramid Network (FPN), we propose the Bilateral Pooling Attention Module (BPAM) that captures discriminative features by jointly modeling dependencies along both the channel and spatial dimensions. Furthermore, the Lane-guided Sparse Attention Mechanism (LSAM) efficiently aggregates global contextual information from the most relevant spatial regions to reinforce lane prior representations while significantly reducing redundant computation. Extensive experiments on benchmark datasets demonstrate that RSANet outperforms state-of-the-art methods in a variety of challenging scenarios. Notably, RSANet achieves an F1@50 score of 80.04% on the CULane dataset that shows notable improvements.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 7","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145297138","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

BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion BoxFusion：通过实时多视图盒融合的无重建开放词汇3D目标检测

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70254

Yuqing Lan, Chenyang Zhu, Zhirui Gao, Jiazhao Zhang, Yihan Cao, Renjiao Yi, Yijie Wang, Kai Xu

{"title":"BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion","authors":"Yuqing Lan, Chenyang Zhu, Zhirui Gao, Jiazhao Zhang, Yihan Cao, Renjiao Yi, Yijie Wang, Kai Xu","doi":"10.1111/cgf.70254","DOIUrl":"https://doi.org/10.1111/cgf.70254","url":null,"abstract":"Open-vocabulary 3D object detection has gained significant interest due to its critical applications in autonomous driving and embodied AI. Existing detection methods, whether offline or online, typically rely on dense point cloud reconstruction, which imposes substantial computational overhead and memory constraints, hindering real-time deployment in downstream tasks. To address this, we propose a novel reconstruction-free online framework tailored for memory-efficient and real-time 3D detection. Specifically, given streaming posed RGB-D video input, we leverage Cubify Anything as a pre-trained visual foundation model (VFM) for single-view 3D object detection, coupled with CLIP to capture open-vocabulary semantics of detected objects. To fuse all detected bounding boxes across different views into a unified one, we employ an association module for correspondences of multi-views and an optimization module to fuse the 3D bounding boxes of the same instance. The association module utilizes 3D Non-Maximum Suppression (NMS) and a box correspondence matching module. The optimization module uses an IoU-guided efficient random optimization technique based on particle filtering to enforce multi-view consistency of the 3D bounding boxes while minimizing computational complexity. Extensive experiments on CA-1M and ScanNetV2 datasets demonstrate that our method achieves state-of-the-art performance among online methods. Benefiting from this novel reconstruction-free paradigm for 3D object detection, our method exhibits great generalization abilities in various scenarios, enabling real-time perception even in environments exceeding 1000 square meters.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 7","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145297139","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

View-Independent Wire Art Modeling via Manifold Fitting 通过流形拟合的视图独立线艺术建模

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70247

HuiGuang Huang, Dong-Yi Wu, Yulin Wang, Yu Cao, Tong-Yee Lee

{"title":"View-Independent Wire Art Modeling via Manifold Fitting","authors":"HuiGuang Huang, Dong-Yi Wu, Yulin Wang, Yu Cao, Tong-Yee Lee","doi":"10.1111/cgf.70247","DOIUrl":"https://doi.org/10.1111/cgf.70247","url":null,"abstract":"This paper presents a novel fully automated method for generating view-independent abstract wire art from 3D models. The main challenge in creating line art is to strike a balance among abstraction, structural clarity, 3D perception, and consistent aesthetics from different viewpoints. Many existing approaches have been proposed, including extracting wire art from mesh, reconstructing it from pictures, etc. But they all suffer from the fact that the wires are usually very unorganized and cumbersome and usually can only guarantee the observation effect of specific viewpoints. To overcome these problems, we propose a paradigm shift: instead of predicting the line segments directly, we consider the generation of wire art as an optimization-driven manifold-fitting problem. Thus we can abstract/generalize the 3D model while retaining the key properties necessary for appealing line art, including structural topology and connectivity, and maintain the three-dimensionality of the line art with a multi-perspective view. Experimental results show that our view-independent method outperforms previous methods in terms of line simplicity, shape fidelity, and visual consistency.","PeriodicalId":10687,"journal":{"name":"Computer Graphics Forum","volume":"44 7","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145297325","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

Introducing Unbiased Depth into 2D Gaussian Splatting for High-accuracy Surface Reconstruction 在二维高斯溅射中引入无偏深度以实现高精度表面重建

IF 2.9 4区计算机科学

Computer Graphics Forum Pub Date : 2025-10-11 DOI: 10.1111/cgf.70252

Yixin Yang, Yang Zhou, Hui Huang

引用次数: 0