Computer Animation and Virtual Worlds最新文献_第4页

A double-layer crowd evacuation simulation method based on deep reinforcement learning 基于深度强化学习的双层人群疏散模拟方法

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-30 DOI: 10.1002/cav.2280

Yong Zhang, Bo Yang, Jianlin Zhu

{"title":"A double-layer crowd evacuation simulation method based on deep reinforcement learning","authors":"Yong Zhang, Bo Yang, Jianlin Zhu","doi":"10.1002/cav.2280","DOIUrl":"https://doi.org/10.1002/cav.2280","url":null,"abstract":"Existing crowd evacuation simulation methods commonly face challenges of low efficiency in path planning and insufficient realism in pedestrian movement during the evacuation process. In this study, we propose a novel crowd evacuation path planning approach based on the learning curve–deep deterministic policy gradient (LC-DDPG) algorithm. The algorithm incorporates dynamic experience pool and a priority experience sampling strategy, enhancing convergence speed and achieving higher average rewards, thus efficiently enabling global path planning. Building upon this foundation, we introduce a double-layer method for crowd evacuation using deep reinforcement learning. Specifically, within each group, individuals are categorized into leaders and followers. At the top layer, we employ the LC-DDPG algorithm to perform global path planning for the leaders. Simultaneously, at the bottom layer, an enhanced social force model guides the followers to avoid obstacles and follow the leaders during evacuation. We implemented a crowd evacuation simulation platform. Experimental results show that our proposed method has high path planning efficiency and can generate more realistic pedestrian trajectories in different scenarios and crowd sizes.","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141187614","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

De-NeRF: Ultra-high-definition NeRF with deformable net alignment De-NeRF：采用可变形网排列的超高清 NeRF

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-30 DOI: 10.1002/cav.2240

Jianing Hou, Runjie Zhang, Zhongqi Wu, Weiliang Meng, Xiaopeng Zhang, Jianwei Guo

{"title":"De-NeRF: Ultra-high-definition NeRF with deformable net alignment","authors":"Jianing Hou, Runjie Zhang, Zhongqi Wu, Weiliang Meng, Xiaopeng Zhang, Jianwei Guo","doi":"10.1002/cav.2240","DOIUrl":"https://doi.org/10.1002/cav.2240","url":null,"abstract":"Neural Radiance Field (NeRF) can render complex 3D scenes with viewpoint-dependent effects. However, less work has been devoted to exploring its limitations in high-resolution environments, especially when upscaled to ultra-high resolution (e.g., 4k). Specifically, existing NeRF-based methods face severe limitations in reconstructing high-resolution real scenes, for example, a large number of parameters, misalignment of the input data, and over-smoothing of details. In this paper, we present a novel and effective framework, called De-NeRF, based on NeRF and deformable convolutional network, to achieve high-fidelity view synthesis in ultra-high resolution scenes: (1) marrying the deformable convolution unit which can solve the problem of misaligned input of the high-resolution data. (2) Presenting a density sparse voxel-based approach which can greatly reduce the training time while rendering results with higher accuracy. Compared to existing high-resolution NeRF methods, our approach improves the rendering quality of high-frequency details and achieves better visual effects in 4K high-resolution scenes.","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141187630","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

Screen-space Streamline Seeding Method for Visualizing Unsteady Flow in Augmented Reality 在增强现实中可视化不稳定流的屏幕空间流线播种法

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-30 DOI: 10.1002/cav.2250

Hyunmo Kang, JungHyun Han

引用次数: 0

PR3D: Precise and realistic 3D face reconstruction from a single image PR3D：从单张图像重建精确逼真的 3D 人脸

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-30 DOI: 10.1002/cav.2254

Zhangjin Huang, Xing Wu

{"title":"PR3D: Precise and realistic 3D face reconstruction from a single image","authors":"Zhangjin Huang, Xing Wu","doi":"10.1002/cav.2254","DOIUrl":"https://doi.org/10.1002/cav.2254","url":null,"abstract":"Reconstructing the three-dimensional (3D) shape and texture of the face from a single image is a significant and challenging task in computer vision and graphics. In recent years, learning-based reconstruction methods have exhibited outstanding performance, but their effectiveness is severely constrained by the scarcity of available training data with 3D annotations. To address this issue, we present the PR3D (Precise and Realistic 3D face reconstruction) method, which consists of high-precision shape reconstruction based on semi-supervised learning and high-fidelity texture reconstruction based on StyleGAN2. In shape reconstruction, we use in-the-wild face images and 3D annotated datasets to train the auxiliary encoder and the identity encoder, encoding the input image into parameters of FLAME (a parametric 3D face model). Simultaneously, a novel semi-supervised hybrid landmark loss is designed to more effectively learn from in-the-wild face images and 3D annotated datasets. Furthermore, to meet the real-time requirements in practical applications, a lightweight shape reconstruction model called fast-PR3D is distilled through teacher–student learning. In texture reconstruction, we propose a texture extraction method based on face reenactment in StyleGAN2 style space, extracting texture from the source and reenacted face images to constitute a facial texture map. Extensive experiments have demonstrated the state-of-the-art performance of our method.","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141187613","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

Design of a lightweight and easy-to-wear hand glove with multi-modal tactile perception for digital human 为数字人类设计轻便易穿的多模式触觉手套

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-30 DOI: 10.1002/cav.2258

Zhigeng Pan, Hongyi Ren, Chang Liu, Ming Chen, Mithun Mukherjee, Wenzhen Yang

{"title":"Design of a lightweight and easy-to-wear hand glove with multi-modal tactile perception for digital human","authors":"Zhigeng Pan, Hongyi Ren, Chang Liu, Ming Chen, Mithun Mukherjee, Wenzhen Yang","doi":"10.1002/cav.2258","DOIUrl":"https://doi.org/10.1002/cav.2258","url":null,"abstract":"Within the field of human–computer interaction, data gloves play an essential role in establishing a connection between virtual and physical environments for the realization of digital human. To enhance the credibility of human-virtual hand interactions, we aim to develop a system incorporating a data glove-embedded technology. Our proposed system collects a wide range of information (temperature, bending, and pressure of fingers) that arise during natural interactions and afterwards reproduce them within the virtual environment. Furthermore, we implement a novel traversal polling technique to facilitate the streamlined aggregation of multi-channel sensors. This mitigates the hardware complexity of the embedded system. The experimental results indicate that the data glove demonstrates a high degree of precision in acquiring real-time hand interaction information, as well as effectively displaying hand posture in real-time using Unity3D. The data glove's lightweight and compact design facilitates its versatile utilization in virtual reality interactions.","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141187615","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

Soccer match broadcast video analysis method based on detection and tracking 基于检测和跟踪的足球比赛转播视频分析方法

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-29 DOI: 10.1002/cav.2259

Hongyu Li, Meng Yang, Chao Yang, Jianglang Kang, Xiang Suo, Weiliang Meng, Zhen Li, Lijuan Mao, Bin Sheng, Jun Qi

{"title":"Soccer match broadcast video analysis method based on detection and tracking","authors":"Hongyu Li, Meng Yang, Chao Yang, Jianglang Kang, Xiang Suo, Weiliang Meng, Zhen Li, Lijuan Mao, Bin Sheng, Jun Qi","doi":"10.1002/cav.2259","DOIUrl":"https://doi.org/10.1002/cav.2259","url":null,"abstract":"We propose a comprehensive soccer match video analysis pipeline tailored for broadcast footage, which encompasses three pivotal stages: soccer field localization, player tracking, and soccer ball detection. Firstly, we introduce sports camera calibration to seamlessly map soccer field images from match videos onto a standardized two-dimensional soccer field template. This addresses the challenge of consistent analysis across video frames amid continuous camera angle changes. Secondly, given challenges such as occlusions, high-speed movements, and dynamic camera perspectives, obtaining accurate position data for players and the soccer ball is non-trivial. To mitigate this, we curate a large-scale, high-precision soccer ball detection dataset and devise a robust detection model, which achieved the <math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>m</mi>\u0000 <mi>A</mi>\u0000 <msub>\u0000 <mrow>\u0000 <mi>P</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>50</mn>\u0000 <mo>−</mo>\u0000 <mn>95</mn>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ mA{P}_{50-95} $$</annotation>\u0000 </semantics></math> of 80.9%. Additionally, we develop a high-speed, efficient, and lightweight tracking model to ensure precise player tracking. Through the integration of these modules, our pipeline focuses on real-time analysis of the current camera lens content during matches, facilitating rapid and accurate computation and analysis while offering intuitive visualizations.","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141165050","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

Graph-based control framework for motion propagation and pattern preservation in swarm flight simulations 基于图的控制框架，用于蜂群飞行模拟中的运动传播和模式保持

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-29 DOI: 10.1002/cav.2276

Feixiang Qi, Bojian Wang, Meili Wang

引用次数: 0

SADNet: Generating immersive virtual reality avatars by real-time monocular pose estimation SADNet：通过实时单目姿势估计生成身临其境的虚拟现实头像

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-29 DOI: 10.1002/cav.2233

Ling Jiang, Yuan Xiong, Qianqian Wang, Tong Chen, Wei Wu, Zhong Zhou

{"title":"SADNet: Generating immersive virtual reality avatars by real-time monocular pose estimation","authors":"Ling Jiang, Yuan Xiong, Qianqian Wang, Tong Chen, Wei Wu, Zhong Zhou","doi":"10.1002/cav.2233","DOIUrl":"https://doi.org/10.1002/cav.2233","url":null,"abstract":"<div>\u0000 \u0000 Generating immersive virtual reality avatars is a challenging task in VR/AR applications, which maps physical human body poses to avatars in virtual scenes for an immersive user experience. However, most existing work is time-consuming and limited by datasets, which does not satisfy immersive and real-time requirements of VR systems. In this paper, we aim to generate 3D real-time virtual reality avatars based on a monocular camera to solve these problems. Specifically, we first design a self-attention distillation network (SADNet) for effective human pose estimation, which is guided by a pre-trained teacher. Secondly, we propose a lightweight pose mapping method for human avatars that utilizes the camera model to map 2D poses to 3D avatar keypoints, generating real-time human avatars with pose consistency. Finally, we integrate our framework into a VR system, displaying generated 3D pose-driven avatars on Helmet-Mounted Display devices for an immersive user experience. We evaluate SADNet on two publicly available datasets. Experimental results show that SADNet achieves a state-of-the-art trade-off between speed and accuracy. In addition, we conducted a user experience study on the performance and immersion of virtual reality avatars. Results show that pose-driven 3D human avatars generated by our method are smooth and attractive.\u0000 </div>","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141165047","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

S-LASSIE: Structure and smoothness enhanced learning from sparse image ensemble for 3D articulated shape reconstruction S-LASSIE：从稀疏图像集合中进行结构和平滑度增强学习，用于三维关节形状重建

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-29 DOI: 10.1002/cav.2277

Jingze Feng, Chong He, Guorui Wang, Meili Wang

{"title":"S-LASSIE: Structure and smoothness enhanced learning from sparse image ensemble for 3D articulated shape reconstruction","authors":"Jingze Feng, Chong He, Guorui Wang, Meili Wang","doi":"10.1002/cav.2277","DOIUrl":"https://doi.org/10.1002/cav.2277","url":null,"abstract":"In computer vision, the task of 3D reconstruction from monocular sparse images poses significant challenges, particularly in the field of animal modelling. The diverse morphology of animals, their varied postures, and the variable conditions of image acquisition significantly complicate the task of accurately reconstructing their 3D shape and pose from a monocular image. To address these complexities, we propose S-LASSIE, a novel technique for 3D reconstruction of quadrupeds from monocular sparse images. It requires only 10–30 images of similar breeds for training. To effectively mitigate depth ambiguities inherent in monocular reconstructions, S-LASSIE employs a multi-angle projection loss function. In addition, our approach, which involves fusion and smoothing of bone structures, resolves issues related to disjointed topological structures and uneven connections at junctions, resulting in 3D models with comprehensive topologies and improved visual fidelity. Our extensive experiments on the Pascal-Part and LASSIE datasets demonstrate significant improvements in keypoint transfer, overall 2D IOU and visual quality, with an average keypoint transfer and overall 2D IOU of 59.6% and 86.3%, respectively, which are superior to existing techniques in the field.","PeriodicalId":50645,"journal":{"name":"Computer Animation and Virtual Worlds","volume":"35 3","pages":""},"PeriodicalIF":1.1,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141165048","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

Face attribute translation with multiple feature perceptual reconstruction assisted by style translator 由风格翻译器辅助的多特征感知重建人脸属性翻译

IF 1.1 4区计算机科学

Computer Animation and Virtual Worlds Pub Date : 2024-05-29 DOI: 10.1002/cav.2273

Shuqi Zhu, Jiuzhen Liang, Hao Liu

引用次数: 0