2023 9th International Conference on Virtual Reality (ICVR)最新文献_第8页

Contemporary Value Research and Digital Protection Practice of Traditional Wooden Boats in Hongze Lake 洪泽湖传统木船的当代价值研究与数字化保护实践

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169511

Deng Bangkun, Liu Zhaoxiang, Seorin Kyeong, Wu Qitao, Yin Guojun, Li Xin

{"title":"Contemporary Value Research and Digital Protection Practice of Traditional Wooden Boats in Hongze Lake","authors":"Deng Bangkun, Liu Zhaoxiang, Seorin Kyeong, Wu Qitao, Yin Guojun, Li Xin","doi":"10.1109/ICVR57957.2023.10169511","DOIUrl":"https://doi.org/10.1109/ICVR57957.2023.10169511","url":null,"abstract":"The water area of Hongze Lake has obvious characteristics and rich aquatic resources. Since ancient times, local traditional wooden boats have been closely related to the daily life of residents and fishing, hunting and labor. In order to protect and inherit the traditional wooden boats in Hongze Lake, and to further explore its contemporary value, the existing documents are sorted out from the perspective of historical culture, interviews are conducted with the inheritors of intangible cultural heritage, and the local folk culture is interpreted to provide reference for the development of ships and handicrafts in Hongze Lake area; Record the wooden ship manufacturing technology from the perspective of process technology, sort out relevant materials, dimensions, structures and manufacturing technology, and provide some basic principles and experience guidance for the modern shipbuilding industry; From the perspective of practical functions, this paper analyzes the scientificity and rationality of the function and modeling coordination of various ship types, analyzes their design value, and helps to understand the creation ideas of local artisans. On the basis of this research, digital modeling and recording will be carried out to achieve the early filing and display, lay the foundation for the later dissemination and innovation, and promote the protection and development of traditional wooden boats in Hongze Lake.","PeriodicalId":439483,"journal":{"name":"2023 9th International Conference on Virtual Reality (ICVR)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122658830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dense Point Cloud Reconstruction Based on a Single Image 基于单幅图像的密集点云重建

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169465

Hanxing Li, Meili Wang

{"title":"Dense Point Cloud Reconstruction Based on a Single Image","authors":"Hanxing Li, Meili Wang","doi":"10.1109/ICVR57957.2023.10169465","DOIUrl":"https://doi.org/10.1109/ICVR57957.2023.10169465","url":null,"abstract":"How to recover high-resolution 3D point clouds from a single image is of great importance in the field of computer vision. However, due to the limited information contained within a single image, reconstructing a dense point cloud of objects from a single image is a highly challenging task. In this paper, we construct a multi-stage dense point cloud reconstruction network that incorporates a coordinate attention mechanism and a point cloud folding operation. The proposed network model comprises two parts: an image-based sparse point cloud generation network and a folding-based dense point cloud generation network. Firstly, we generate a sparse point cloud by extracting the features of the target object from a single image using an image-based sparse point cloud generation network. Then we use the folding-based dense point cloud generation network to density the generated sparse point cloud. Finally, the two stages are combined by deep learning fine-tuning techniques to form an end-to-end dense point cloud reconstruction network that generates a dense point cloud from a single image. By evaluating the synthetic datasets, the proposed method effectively reconstructs the dense point cloud model of the corresponding object and outperforms existing methods in terms of metrics. Meanwhile, our method also performs well on real-world datasets.","PeriodicalId":439483,"journal":{"name":"2023 9th International Conference on Virtual Reality (ICVR)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127640925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bionic Robots as a New Alternative to Guided Dogs 仿生机器人作为导盲犬的新选择

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169301

Yilin Cao, Nanlin Jin, Yihong Wang, Chengtao Ji, Yushan Pan

引用次数: 0

A Scene Understanding and Positioning System from RGB Images for Tele-meeting Application in Augmented Reality 基于RGB图像的增强现实远程会议场景理解与定位系统

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169590

Bo-Hui Wang, Febrina Wijaya, Robin Fischer, Ya-Hui Tang, Shiann-Jang Wang, Wei-En Hsu, L. Fu

{"title":"A Scene Understanding and Positioning System from RGB Images for Tele-meeting Application in Augmented Reality","authors":"Bo-Hui Wang, Febrina Wijaya, Robin Fischer, Ya-Hui Tang, Shiann-Jang Wang, Wei-En Hsu, L. Fu","doi":"10.1109/ICVR57957.2023.10169590","DOIUrl":"https://doi.org/10.1109/ICVR57957.2023.10169590","url":null,"abstract":"As augmented reality (AR) technology advances, there is a growing demand to apply it to various applications. With the outbreak of the COVID-19 epidemic in 2020, online meetings have become increasingly common to prevent human contact, creating an opportunity to implement AR technology and its related applications. In this paper, we propose a new AR solution for tele-meeting applications that combines neural networks and simultaneous localization and mapping (SLAM) to achieve scene understanding and user localization using only RGB images. Our system offers the flexibility to develop the target application solely based on our custom devices/software, rather than relying on existing AR software development kits (SDKs) with their limitations. Existing SDKs, such as ARCore, can only be used on officially certified devices by Google, and developing custom AR kits to resolve compatibility issues among multiple technologies and devices can be challenging and time-consuming. This work presents a new system to address the challenges of scene understanding and user positioning for realizing tele-meeting applications, which can also be used as an AR development kit on any device with a camera. We conducted several experiments on the system modules to verify its performance, and the results show that our system provides an efficient and stable user experience, making it a promising technology and application.","PeriodicalId":439483,"journal":{"name":"2023 9th International Conference on Virtual Reality (ICVR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129884277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the Design Space for Hands-Free Robot Dog Interaction via Augmented Reality 利用增强现实技术探索无手机器狗交互的设计空间

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169556

Ziming Li, Zihui Qin, Yiming Luo, Yushan Pan, Hai-Ning Liang

{"title":"Exploring the Design Space for Hands-Free Robot Dog Interaction via Augmented Reality","authors":"Ziming Li, Zihui Qin, Yiming Luo, Yushan Pan, Hai-Ning Liang","doi":"10.1109/ICVR57957.2023.10169556","DOIUrl":"https://doi.org/10.1109/ICVR57957.2023.10169556","url":null,"abstract":"With the advancement of robotics-related technologies, there is a growing potential for robot dogs to replace real dogs in helping humans at work, in dangerous situations, or as companions. However, at present, robot dogs are mainly used in the engineering sector, for the companionship of older people and children, and to assist disabled people. However, their interaction is very limited. This prevents many user groups from benefiting from having a robot dog. Advances in Augmented Reality (AR) technology offer more possible methods for controlling robot dogs. This work explores the elements that could be designed for user-robot dog interaction via an AR interface. Furthermore, to consider the situation where users are occupied with another task or unable to use their hands when they are with a robot dog (e.g., jogging or walking with their hands holding items), we focus on hands-free interaction. To accomplish this exploration, we deconstruct the control process and develop a design space for hands-free interaction via AR. This space can help designers identify and use all potential options when designing AR interfaces for effective human-robot dog interaction. We also present a demonstration to illustrate how to use our design space.","PeriodicalId":439483,"journal":{"name":"2023 9th International Conference on Virtual Reality (ICVR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130694971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring Selection and Search Usability Across Desktop, Tablet, and Head-Mounted Display WebXR Platforms 探索桌面、平板电脑和头戴式显示器WebXR平台上的选择和搜索可用性

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169549

Anthony Scavarelli, Robert J. Teather, A. Arya

引用次数: 0

MultiBrush: 3D Brush Painting Using Multiple Viewpoints in Virtual Reality MultiBrush:在虚拟现实中使用多视点的3D笔刷绘画

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169798

Mikiya Kusunoki, Ryo Furuhama, Ryusuke Toshima, Hazuki Mori, Haoran Xie, Tzu-Yang Wang, T. Yuizono, Toshiki Sato, K. Miyata

引用次数: 0

VR-Assisted Healing: VR CONTENT Creation Cuts through the Psychological Healing Process VR辅助治疗:VR内容创作贯穿心理治疗过程

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169380

Aokun Yu, Cheng Zhang, JinNi Huang, YuTian Yi

引用次数: 0

Detecting Zero-Shot Human-Object Interaction with Visual-Text Modeling 用视觉文本建模检测零射击人-物交互

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169554

Haozhong Wang, Hua Yu, Qiang Zhang

{"title":"Detecting Zero-Shot Human-Object Interaction with Visual-Text Modeling","authors":"Haozhong Wang, Hua Yu, Qiang Zhang","doi":"10.1109/ICVR57957.2023.10169554","DOIUrl":"https://doi.org/10.1109/ICVR57957.2023.10169554","url":null,"abstract":"Most existing Human-Object Interaction (HOI) detection methods focus on supervised learning, but labeling all interactions is costly because of the enormous possible combinations of objects and verbs. Zero-shot HOI detection emerges as a promising approach to address this problem but encounters challenges when facing unseen interactions. To this end, we propose a novel two-stage Visual-Text modeling HOI detection (VT-HOI) method which can effectively recognize both seen and unseen interactions. In the first stage, the features of the humans and the objects are extracted by DETR and concatenated as the query sequences. In the second stage, local and global memory features from the Visual Encoder are fused into the corresponding query sequences by our proposed Semantic Representation Decoder with the cross-attention mechanism. Then we perform cosine similarity computation between visual features and text features, which are extracted or label-generated by Visual Representation Head (VRH) and Text Feature Memory (TFM) module respectively. Finally, the similarity matrix is fused with the results of the classification head for training or inference. The comprehensive experiments conducted on HICO-DET datasets demonstrate that the proposed VT-HOI significantly outperforms the state-of-the-art methods.","PeriodicalId":439483,"journal":{"name":"2023 9th International Conference on Virtual Reality (ICVR)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130719453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bridge Crane Co-simulation Based on Solidworks/Adams/Matlab 基于Solidworks/Adams/Matlab的桥式起重机联合仿真

2023 9th International Conference on Virtual Reality (ICVR) Pub Date : 2023-05-12 DOI: 10.1109/ICVR57957.2023.10169531

Xiuxian Yang, Yuchi Cao, Tie-shan Li, Qihe Shan

引用次数: 0