Woojin Cho, Taewook Ha, Ikbeom Jeon, Jinwoo Jeon, Tae-Kyun Kim, Woontack Woo
{"title":"Temporally enhanced graph convolutional network for hand tracking from an egocentric camera","authors":"Woojin Cho, Taewook Ha, Ikbeom Jeon, Jinwoo Jeon, Tae-Kyun Kim, Woontack Woo","doi":"10.1007/s10055-024-01039-3","DOIUrl":null,"url":null,"abstract":"<p>We propose a robust 3D hand tracking system in various hand action environments, including hand-object interaction, which utilizes a single color image and a previous pose prediction as input. We observe that existing methods deterministically exploit temporal information in motion space, failing to address realistic diverse hand motions. Also, prior methods paid less attention to efficiency as well as robust performance, i.e., the balance issues between time and accuracy. The Temporally Enhanced Graph Convolutional Network (TE-GCN) utilizes a 2-stage framework to encode temporal information adaptively. The system establishes balance by adopting an adaptive GCN, which effectively learns the spatial dependency between hand mesh vertices. Furthermore, the system leverages the previous prediction by estimating the relevance across image features through the attention mechanism. The proposed method achieves state-of-the-art balanced performance on challenging benchmarks and demonstrates robust results on various hand motions in real scenes. Moreover, the hand tracking system is integrated into a recent HMD with an off-loading framework, achieving a real-time framerate while maintaining high performance. Our study improves the usability of a high-performance hand-tracking method, which can be generalized to other algorithms and contributes to the usage of HMD in everyday life. Our code with the HMD project will be available at https://github.com/UVR-WJCHO/TEGCN_on_Hololens2.</p>","PeriodicalId":23727,"journal":{"name":"Virtual Reality","volume":"2019 1","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Virtual Reality","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10055-024-01039-3","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
We propose a robust 3D hand tracking system in various hand action environments, including hand-object interaction, which utilizes a single color image and a previous pose prediction as input. We observe that existing methods deterministically exploit temporal information in motion space, failing to address realistic diverse hand motions. Also, prior methods paid less attention to efficiency as well as robust performance, i.e., the balance issues between time and accuracy. The Temporally Enhanced Graph Convolutional Network (TE-GCN) utilizes a 2-stage framework to encode temporal information adaptively. The system establishes balance by adopting an adaptive GCN, which effectively learns the spatial dependency between hand mesh vertices. Furthermore, the system leverages the previous prediction by estimating the relevance across image features through the attention mechanism. The proposed method achieves state-of-the-art balanced performance on challenging benchmarks and demonstrates robust results on various hand motions in real scenes. Moreover, the hand tracking system is integrated into a recent HMD with an off-loading framework, achieving a real-time framerate while maintaining high performance. Our study improves the usability of a high-performance hand-tracking method, which can be generalized to other algorithms and contributes to the usage of HMD in everyday life. Our code with the HMD project will be available at https://github.com/UVR-WJCHO/TEGCN_on_Hololens2.
期刊介绍:
The journal, established in 1995, publishes original research in Virtual Reality, Augmented and Mixed Reality that shapes and informs the community. The multidisciplinary nature of the field means that submissions are welcomed on a wide range of topics including, but not limited to:
Original research studies of Virtual Reality, Augmented Reality, Mixed Reality and real-time visualization applications
Development and evaluation of systems, tools, techniques and software that advance the field, including:
Display technologies, including Head Mounted Displays, simulators and immersive displays
Haptic technologies, including novel devices, interaction and rendering
Interaction management, including gesture control, eye gaze, biosensors and wearables
Tracking technologies
VR/AR/MR in medicine, including training, surgical simulation, rehabilitation, and tissue/organ modelling.
Impactful and original applications and studies of VR/AR/MR’s utility in areas such as manufacturing, business, telecommunications, arts, education, design, entertainment and defence
Research demonstrating new techniques and approaches to designing, building and evaluating virtual and augmented reality systems
Original research studies assessing the social, ethical, data or legal aspects of VR/AR/MR.