We propose a method that estimates 6-DoF camera pose from a partially visible large object, by exploiting information of its subparts that are detected using a state-of-the-art convolutional neural network (CNN). The trained CNN outputs two-dimensional bounding boxes around subparts and associated classes. Information from detection is then fed to a deep neural network that regresses to camera's 6-DoF poses. Experimental results show that the proposed method is more robust to occlusions than conventional learning-based methods.
{"title":"Learning-based Estimation of 6-DoF Camera Poses from Partial Observation of Large Objects for Mobile AR*","authors":"Jean-Pierre Lomaliza, Hanhoon Park","doi":"10.1145/3359996.3364718","DOIUrl":"https://doi.org/10.1145/3359996.3364718","url":null,"abstract":"We propose a method that estimates 6-DoF camera pose from a partially visible large object, by exploiting information of its subparts that are detected using a state-of-the-art convolutional neural network (CNN). The trained CNN outputs two-dimensional bounding boxes around subparts and associated classes. Information from detection is then fed to a deep neural network that regresses to camera's 6-DoF poses. Experimental results show that the proposed method is more robust to occlusions than conventional learning-based methods.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130996008","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}
Sang-Woo Seo, Seungjoon Kwon, Waseem Hassan, A. Talhan, Seokhee Jeon
We present an interactive virtual-reality (VR) fire extinguisher that provides both realistic viewing using a head-mounted display (HMD) and kinesthetic experiences using a pneumatic muscle and vibrotactile transducer. The VR fire extinguisher is designed to train people to use a fire extinguisher skillfully in real fire situations. We seamlessly integrate three technologies: VR, object motion tracking, and haptic feedback. A fire scene is immersed in the HMD, and a motion tracker is used to replicate a real designed object into the virtual environment to realize augmented reality. In addition, when the handle of the fire extinguisher is squeezed to release the extinguishing agent, the haptic device generates both vibrotactile and air flow tactile feedback signals, providing the same experience as that obtained while using a real fire extinguisher.
{"title":"Interactive Virtual-Reality Fire Extinguisher with Haptic Feedback","authors":"Sang-Woo Seo, Seungjoon Kwon, Waseem Hassan, A. Talhan, Seokhee Jeon","doi":"10.1145/3359996.3364725","DOIUrl":"https://doi.org/10.1145/3359996.3364725","url":null,"abstract":"We present an interactive virtual-reality (VR) fire extinguisher that provides both realistic viewing using a head-mounted display (HMD) and kinesthetic experiences using a pneumatic muscle and vibrotactile transducer. The VR fire extinguisher is designed to train people to use a fire extinguisher skillfully in real fire situations. We seamlessly integrate three technologies: VR, object motion tracking, and haptic feedback. A fire scene is immersed in the HMD, and a motion tracker is used to replicate a real designed object into the virtual environment to realize augmented reality. In addition, when the handle of the fire extinguisher is squeezed to release the extinguishing agent, the haptic device generates both vibrotactile and air flow tactile feedback signals, providing the same experience as that obtained while using a real fire extinguisher.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126195871","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}
This study investigates the influence of a virtual human (VH) with recorded human voice vs VH with a machine-generated voice (text-to-speech) on building trust and working alliance. We measured the co-presence perception to understand the impact of VH's perception on building the human-VH relationship. The results revealed no differences between the two types of voices on co-presence perception, trust or working alliance.
{"title":"A Comparison of Human and Machine-Generated Voice","authors":"Amal Abdulrahman, Deborah Richards, A. Bilgin","doi":"10.1145/3359996.3364754","DOIUrl":"https://doi.org/10.1145/3359996.3364754","url":null,"abstract":"This study investigates the influence of a virtual human (VH) with recorded human voice vs VH with a machine-generated voice (text-to-speech) on building trust and working alliance. We measured the co-presence perception to understand the impact of VH's perception on building the human-VH relationship. The results revealed no differences between the two types of voices on co-presence perception, trust or working alliance.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"15 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120921190","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}
Observing eye movement is a direct way to analyse human’s attention. Eye movement patterns in normal environment have been widely investigated. In virtual reality (VR) environment, previous studies of eye movement patterns are mainly based on content-unrelated influential factors. Considering this issue, in this paper, a novel content-related factor is studied. One crucial kind of region of interest (ROI), namely vision-penetrable entrance, is chosen to analyse eye movement pattern differences. The results suggest that users show more interest in vision-penetrable entrances than in other regions. Furthermore, this kind of difference is identified as higher average density of fixation. As far as we know, this paper is the first attempt to study specific types of ROI in virtual reality environments. The method utilised in this paper can be applied in other ROI analysis.
{"title":"A Content-Aware Approach for Analysing Eye Movement Patterns in Virtual Reality","authors":"Xiang-Zhi Cao, Richard Skarbez, Zhen He, H. Duh","doi":"10.1145/3359996.3364723","DOIUrl":"https://doi.org/10.1145/3359996.3364723","url":null,"abstract":"Observing eye movement is a direct way to analyse human’s attention. Eye movement patterns in normal environment have been widely investigated. In virtual reality (VR) environment, previous studies of eye movement patterns are mainly based on content-unrelated influential factors. Considering this issue, in this paper, a novel content-related factor is studied. One crucial kind of region of interest (ROI), namely vision-penetrable entrance, is chosen to analyse eye movement pattern differences. The results suggest that users show more interest in vision-penetrable entrances than in other regions. Furthermore, this kind of difference is identified as higher average density of fixation. As far as we know, this paper is the first attempt to study specific types of ROI in virtual reality environments. The method utilised in this paper can be applied in other ROI analysis.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114165214","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}
Natalie McHugh, Sungchul Jung, S. Hoermann, R. Lindeman
This study explores ways to increase comfort in Virtual Reality by minimizing cybersickness. Cybersickness is related to classical motion sickness and causes unwanted symptoms when using immersive technologies. We developed a dial interface to accurately capture momentary user cybersickness and feed this information back to the user. Using a seated VR roller coaster environment, we found that the dial is significantly positively correlated with post-immersion questionnaires and is a valid tool compared to verbal rating approaches.
{"title":"Investigating a Physical Dial as a Measurement Tool for Cybersickness in Virtual Reality","authors":"Natalie McHugh, Sungchul Jung, S. Hoermann, R. Lindeman","doi":"10.1145/3359996.3364259","DOIUrl":"https://doi.org/10.1145/3359996.3364259","url":null,"abstract":"This study explores ways to increase comfort in Virtual Reality by minimizing cybersickness. Cybersickness is related to classical motion sickness and causes unwanted symptoms when using immersive technologies. We developed a dial interface to accurately capture momentary user cybersickness and feed this information back to the user. Using a seated VR roller coaster environment, we found that the dial is significantly positively correlated with post-immersion questionnaires and is a valid tool compared to verbal rating approaches.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125042020","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}
Interactive 3D modeling in VR is both aided by immersive 3D input and hampered by model disjunct, tool-based or selection-action user interfaces. We propose a direct, signifier-based approach to the popular interactive technique of creating 3D models through a sequence of extrusion operations. Motivated by handles and signifiers that communicate the affordances of everyday objects, we define a set of design principles for an immersive, signifier-based modeling interface. We then present an interactive 3D modeling system where all modeling affordances are modelessly reachable and signified on the model itself.
{"title":"Signifier-Based Immersive and Interactive 3D Modeling","authors":"J. A. Bærentzen, J. Frisvad, K. Singh","doi":"10.1145/3359996.3364257","DOIUrl":"https://doi.org/10.1145/3359996.3364257","url":null,"abstract":"Interactive 3D modeling in VR is both aided by immersive 3D input and hampered by model disjunct, tool-based or selection-action user interfaces. We propose a direct, signifier-based approach to the popular interactive technique of creating 3D models through a sequence of extrusion operations. Motivated by handles and signifiers that communicate the affordances of everyday objects, we define a set of design principles for an immersive, signifier-based modeling interface. We then present an interactive 3D modeling system where all modeling affordances are modelessly reachable and signified on the model itself.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130164500","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}
Augmented Reality (AR) mirrors can show virtual objects overlaid onto the physical world reflected in the mirror. Optical-reflection type AR mirror displays use half-silvered mirrors attached in front of a digital display. However, prior work suffered from visual depth mismatch between the optical reflection of the 3D physical space and 2D images displayed on the surface of the mirror. In this research, we use 3D visualisation to overcome this problem and improve the user experience by providing better depth perception for watching and interacting with the content displayed on an AR mirror. As a proof of concept, we developed two prototype optical-reflection type 3D AR mirror displays, one using glasses-free multi-view 3D display and another using a head tracked 3D stereoscopic display that supports hand gesture interaction.
{"title":"Optical-Reflection Type 3D Augmented Reality Mirrors","authors":"Gun A. Lee, H. Park, M. Billinghurst","doi":"10.1145/3359996.3364782","DOIUrl":"https://doi.org/10.1145/3359996.3364782","url":null,"abstract":"Augmented Reality (AR) mirrors can show virtual objects overlaid onto the physical world reflected in the mirror. Optical-reflection type AR mirror displays use half-silvered mirrors attached in front of a digital display. However, prior work suffered from visual depth mismatch between the optical reflection of the 3D physical space and 2D images displayed on the surface of the mirror. In this research, we use 3D visualisation to overcome this problem and improve the user experience by providing better depth perception for watching and interacting with the content displayed on an AR mirror. As a proof of concept, we developed two prototype optical-reflection type 3D AR mirror displays, one using glasses-free multi-view 3D display and another using a head tracked 3D stereoscopic display that supports hand gesture interaction.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129618442","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}
Teleportation is a popular and low risk means of navigating in VR. Because teleportation discontinuously translates the user’s viewpoint, no optical flow is generated that could lead to vection-induced VR sickness. However, instant viewpoint translations and resulting discontinuous avatar representation is not only detrimental to presence and spatial awareness but also presents a challenge for gameplay design–particularly for multiplayer games. We compare out-of-body locomotion, a hybrid viewpoint technique that lets users seamlessly switch between a first-person and third-person avatar view, to traditional pointer-based teleportation. While in third-person, if the user doesn’t move, the camera remains stationary to avoid any optical flow generation. Third-person also lets users precisely and continuously navigate their avatar without risk of getting VR sick. The viewpoint automatically switches back to first-person as soon the users breaks line of sight with their avatar or the user requests to rejoin the avatar with a button press. A user study compares out-of-body locomotion to teleportation with participants (n=22) traversing an obstacle course. Results show that out-of-body locomotion requires significantly fewer (67%) viewpoint transitions than teleportation while there was no significant difference in performance. In addition to being able to offer a continuous avatar representation, participants also deemed out-of-body locomotion to be faster.
{"title":"Out-of-body Locomotion: Vectionless Navigation with a Continuous Avatar Representation","authors":"Nathan Navarro Griffin, Eelke Folmer","doi":"10.1145/3359996.3364243","DOIUrl":"https://doi.org/10.1145/3359996.3364243","url":null,"abstract":"Teleportation is a popular and low risk means of navigating in VR. Because teleportation discontinuously translates the user’s viewpoint, no optical flow is generated that could lead to vection-induced VR sickness. However, instant viewpoint translations and resulting discontinuous avatar representation is not only detrimental to presence and spatial awareness but also presents a challenge for gameplay design–particularly for multiplayer games. We compare out-of-body locomotion, a hybrid viewpoint technique that lets users seamlessly switch between a first-person and third-person avatar view, to traditional pointer-based teleportation. While in third-person, if the user doesn’t move, the camera remains stationary to avoid any optical flow generation. Third-person also lets users precisely and continuously navigate their avatar without risk of getting VR sick. The viewpoint automatically switches back to first-person as soon the users breaks line of sight with their avatar or the user requests to rejoin the avatar with a button press. A user study compares out-of-body locomotion to teleportation with participants (n=22) traversing an obstacle course. Results show that out-of-body locomotion requires significantly fewer (67%) viewpoint transitions than teleportation while there was no significant difference in performance. In addition to being able to offer a continuous avatar representation, participants also deemed out-of-body locomotion to be faster.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130889750","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}
An interactive, one-bounce, and indirect illumination algorithm, which considers indirect visibility, is introduced. First, a ray marching algorithm (MRM), which is based on a 3D mipmap hierarchy structure generated by voxelizing the scene to accelerate the ray-voxel intersection, is used. Second, the indirect images are denoised by iterating an improved, edge-avoiding filtering with a local means replacement (LMR) method. The implementation demonstrates that our solutions can efficiently generate high-quality global illumination images even in a fully dynamic scene.
{"title":"Interactive Indirect Illumination Using Mipmap-based Ray Marching and Local Means Replaced Denoising","authors":"Bo Zhang, Kyoungsu Oh","doi":"10.1145/3359996.3364777","DOIUrl":"https://doi.org/10.1145/3359996.3364777","url":null,"abstract":"An interactive, one-bounce, and indirect illumination algorithm, which considers indirect visibility, is introduced. First, a ray marching algorithm (MRM), which is based on a 3D mipmap hierarchy structure generated by voxelizing the scene to accelerate the ray-voxel intersection, is used. Second, the indirect images are denoised by iterating an improved, edge-avoiding filtering with a local means replacement (LMR) method. The implementation demonstrates that our solutions can efficiently generate high-quality global illumination images even in a fully dynamic scene.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128476884","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}
This paper presents a method for generating in real-time a self-avatar using a single RGB-D Camera. The self-avatar was presented under the form of a point cloud, retrieved thanks to a Kinect V2. The method included smoothing, filtering, segmenting and remapping point data presenting the user's body in real-time. The point cloud avatar in the third and the first person view can be generated.
{"title":"Real Time Point Cloud Self-Avatar With A Single RGB-D Camera","authors":"Hela Ridha-Mahfoudhi, Nguyen Thong Dang","doi":"10.1145/3359996.3365041","DOIUrl":"https://doi.org/10.1145/3359996.3365041","url":null,"abstract":"This paper presents a method for generating in real-time a self-avatar using a single RGB-D Camera. The self-avatar was presented under the form of a point cloud, retrieved thanks to a Kinect V2. The method included smoothing, filtering, segmenting and remapping point data presenting the user's body in real-time. The point cloud avatar in the third and the first person view can be generated.","PeriodicalId":393864,"journal":{"name":"Proceedings of the 25th ACM Symposium on Virtual Reality Software and Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115488400","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：