Computers & Graphics-Uk最新文献_第8页

Design and evaluation of a virtual rehabilitation system integrating intangible cultural heritage: A case study of Baduanjin-based somatosensory training 整合非物质文化遗产的虚拟康复系统设计与评价——以八段锦体感训练为例

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-21 DOI: 10.1016/j.cag.2025.104378

Yifan Zhang , Lanqi Xu , Xu Lang , Jianing Liu , Pengfei Leng , Xuanchi Gong , Xiao Song , Zhigeng Pan

{"title":"Design and evaluation of a virtual rehabilitation system integrating intangible cultural heritage: A case study of Baduanjin-based somatosensory training","authors":"Yifan Zhang , Lanqi Xu , Xu Lang , Jianing Liu , Pengfei Leng , Xuanchi Gong , Xiao Song , Zhigeng Pan","doi":"10.1016/j.cag.2025.104378","DOIUrl":"10.1016/j.cag.2025.104378","url":null,"abstract":"<div><div>Motor coordination disorders significantly impair patients’ ability to perform daily activities. Traditional rehabilitation approaches often suffer from low adherence due to their monotony. This study presents The Wonderful Journey Based on Baduanjin (TWJB), a gamified virtual rehabilitation system that integrates somatosensory interaction with the traditional Chinese exercise Baduanjin. The system employs embodied narrative scenarios and avatar-guided mechanisms to facilitate culturally embedded rehabilitation training. By incorporating real-time motion capture, dynamic feedback, and interactive knowledge cards, the system enhances user immersion and rehabilitation motivation. A controlled experiment was conducted to evaluate its effectiveness. Results indicate that TWJB outperforms conventional rehabilitation methods in terms of user engagement, cultural knowledge acquisition, and functional recovery. These findings underscore the potential of combining traditional culture with intelligent interaction technologies in modern rehabilitation medicine.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104378"},"PeriodicalIF":2.8,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144908411","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

Analyzing singular patterns in discrete planar vector fields via persistent path homology 基于持续路径同调的离散平面矢量场奇异模式分析

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-21 DOI: 10.1016/j.cag.2025.104354

Yu Chen, Hongwei Lin

引用次数: 0

Learning-based geometric framework for noise discernment and denoising of 2D point sets 基于学习的二维点集噪声识别与去噪几何框架

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-21 DOI: 10.1016/j.cag.2025.104327

Minu Reghunath , Keerthiharan Ananth , Joms Antony , Keerthana Muralidharan , Ramanathan Muthuganapathy

引用次数: 0

Multi-scale cascaded network with high-low frequency for low-light image enhancement 用于弱光图像增强的高低频多尺度级联网络

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-21 DOI: 10.1016/j.cag.2025.104380

Jianxing Wu , Teng Ran , Wendong Xiao , Liang Yuan , Qing Tao

{"title":"Multi-scale cascaded network with high-low frequency for low-light image enhancement","authors":"Jianxing Wu , Teng Ran , Wendong Xiao , Liang Yuan , Qing Tao","doi":"10.1016/j.cag.2025.104380","DOIUrl":"10.1016/j.cag.2025.104380","url":null,"abstract":"<div><div>Low-light images affect human visual perception and computer vision downstream tasks because of low illumination, blurred details, and severe noise. Most existing methods optimize the illumination prior and reflectance of the image to accomplish low-light image enhancement. However, in these methods, the acquired illumination features cannot be effectively restored, and the spatial structure cannot be adequately rendered. To address the above issues, this paper proposes a high and low-frequency enhanced low-light image enhancement framework based on a cascaded UNet. To obtain high-quality illumination features, we design a UNet architecture to capture both local and global semantic priors, which are then used to illuminate low-light images. The second UNet module extracts local details and fine spatial structures to repair degraded image information using illumination-guided restoration with high and low-frequency enhancements. At the second UNet skip connections, we quote the channel reduction attention mechanism to enhance the interaction of feature channel information. Experiments on public datasets show that the proposed method achieves superior enhancement performance.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104380"},"PeriodicalIF":2.8,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144908414","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

MonoPartNeRF: Human reconstruction from monocular video via part-based neural radiance fields MonoPartNeRF：基于局部神经辐射场的单眼视频人体重建

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-20 DOI: 10.1016/j.cag.2025.104385

Yao Lu , Jiawei Li , Ming Jiang

{"title":"MonoPartNeRF: Human reconstruction from monocular video via part-based neural radiance fields","authors":"Yao Lu , Jiawei Li , Ming Jiang","doi":"10.1016/j.cag.2025.104385","DOIUrl":"10.1016/j.cag.2025.104385","url":null,"abstract":"<div><div>In recent years, Neural Radiance Fields (NeRF) have achieved remarkable progress in dynamic human reconstruction and rendering. Part-based rendering paradigms, guided by human segmentation, allow for flexible parameter allocation based on structural complexity, thereby enhancing representational efficiency. However, existing methods still struggle with complex pose variations, often producing unnatural transitions at part boundaries and failing to reconstruct occluded regions accurately in monocular settings. We propose MonoPartNeRF, a novel framework for monocular dynamic human rendering that ensures smooth transitions and robust occlusion recovery. First, we build a bidirectional deformation model that combines rigid and non-rigid transformations to establish a continuous, reversible mapping between observation and canonical spaces. Sampling points are projected into a parameterized surface-time space (u, v, t) to better capture non-rigid motion. A consistency loss further suppresses deformation-induced artifacts and discontinuities. We introduce a part-based pose embedding mechanism that decomposes global pose vectors into local joint embeddings based on body regions. This is combined with keyframe pose retrieval and interpolation, along three orthogonal directions, to guide pose-aware feature sampling. A learnable appearance code is integrated via attention to model dynamic texture changes effectively. Experiments on the ZJU-MoCap and MonoCap datasets demonstrate that our method significantly outperforms prior approaches under complex pose and occlusion conditions, achieving superior joint alignment, texture fidelity, and structural continuity.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104385"},"PeriodicalIF":2.8,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889478","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

CDR-CARNet: Baggage re-identification based on cross-domain robust features and camera-aware re-ranking CDR-CARNet：基于跨域鲁棒特征和相机感知重排序的行李再识别

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-19 DOI: 10.1016/j.cag.2025.104377

Yinghong Liu , Hongying Zhang , Xi Yang , Sijia Zhao , Jinhong Zhang

{"title":"CDR-CARNet: Baggage re-identification based on cross-domain robust features and camera-aware re-ranking","authors":"Yinghong Liu , Hongying Zhang , Xi Yang , Sijia Zhao , Jinhong Zhang","doi":"10.1016/j.cag.2025.104377","DOIUrl":"10.1016/j.cag.2025.104377","url":null,"abstract":"<div><div>To address the challenges of cross-domain distribution inconsistency, large intra-class appearance and viewpoint variations in airport baggage re-identification, this paper proposes CDR-CARNet, which integrates cross-domain robust feature learning, dynamic hard sample mining, and camera-aware re-ranking. Firstly, the integration of Instance-Batch Normalization and Global Context attention mechanisms is employed to alleviate inter-domain shifts. Secondly, Margin Sample Mining Loss is adopted to dynamically select the hardest positive and negative sample pairs, thereby optimizing the decision boundary between samples. Finally, the CA-Jaccard re-ranking strategy is introduced to suppress cross-camera noise interference. Experiments conducted on the MVB dataset demonstrate that CDR-CARNet achieves 87.0% mAP, 86.1% Rank-1, and 84.6% mINP, representing improvements of 4.6%, 4.5%, and 5.9% over the AGW baseline, respectively. The method also significantly outperforms existing mainstream approaches, verifying its practicality and robustness for cross-camera baggage matching in complex airport scenarios.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104377"},"PeriodicalIF":2.8,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895037","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

Canonical pose reconstruction from single depth image for 3D non-rigid pose recovery on limited datasets 基于单深度图像的典型位姿重建，用于有限数据集上的三维非刚性位姿恢复

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-19 DOI: 10.1016/j.cag.2025.104370

Fahd Alhamazani , Paul L. Rosin , Yu-Kun Lai

引用次数: 0

Real-time voxelized mesh fracture with Gram–Schmidt constraints 具有Gram-Schmidt约束的实时体素网格断裂

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-19 DOI: 10.1016/j.cag.2025.104382

Tim McGraw, Xinyi Zhou

引用次数: 0

Semantics and perceptual coding for cloud-edge collaborative game streaming 云边缘协同游戏流的语义和感知编码

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-19 DOI: 10.1016/j.cag.2025.104367

An Kang , KeXun Pu , ZeJun Lyu , Yanci Zhang

引用次数: 0

SAM2Med3D: Leveraging video foundation models for 3D breast MRI segmentation SAM2Med3D：利用视频基础模型进行3D乳房MRI分割

IF 2.8 4区计算机科学

Computers & Graphics-Uk Pub Date : 2025-08-19 DOI: 10.1016/j.cag.2025.104341

Ying Chen , Wenjing Cui , Xiaoyan Dong , Shuai Zhou , Zhongqiu Wang

{"title":"SAM2Med3D: Leveraging video foundation models for 3D breast MRI segmentation","authors":"Ying Chen , Wenjing Cui , Xiaoyan Dong , Shuai Zhou , Zhongqiu Wang","doi":"10.1016/j.cag.2025.104341","DOIUrl":"10.1016/j.cag.2025.104341","url":null,"abstract":"<div><div>Foundation models such as the Segment Anything Model 2 (SAM2) have demonstrated impressive generalization across natural image domains. However, their potential in volumetric medical imaging remains largely underexplored, particularly under limited data conditions. In this paper, we present SAM2Med3D, a novel multi-stage framework that adapts a general-purpose video foundation model for accurate and consistent 3D breast MRI segmentation by treating 3D MRI scan as a sequence of images. Unlike existing image-based approaches (e.g., MedSAM) that require large-scale medical data for fine-tuning, our method combines a lightweight, task-specific segmentation network with a video foundation model, achieving strong performance with only modest training data. To guide the foundation model effectively, we introduce a novel spatial filtering strategy that identifies reliable slices from the initial segmentation to serve as high-quality prompts. Additionally, we propose a confidence-driven fusion mechanism that adaptively integrates coarse and refined predictions across the volume, mitigating segmentation drift and ensuring both local accuracy and global volumetric consistency. We validate SAM2Med3D on two multi-center breast MRI datasets, including both public and self-collected datasets. Experimental results demonstrate that our method outperforms both task-specific segmentation networks and recent foundation-model-based methods, achieving superior accuracy and inter-slice consistency.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104341"},"PeriodicalIF":2.8,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865704","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