In this demo, we present a Virtual Reality (VR) Prototype that assists geoscientist in the task of seismic interpretation. The system renders a 3D seismic volume in a virtual reality environment where users may see semantic information and add annotations. The data integration is provided by a hybrid knowledge base that handles multimodal data like 3D models and multimedia content. The knowledge base can support other systems as well, which permits reasoning over the data. Therefore, our proposed system is intended to assist users in seismic interpretation by combining visual inspection with immersion, semantic information retrieval, and structured storage.
{"title":"A Knowledge Oriented Virtual Reality Tool for Exploring Seismic Data","authors":"W. Santos, Reinaldo Silva, R. Santos, M. Moreno","doi":"10.1109/AIVR.2018.00045","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00045","url":null,"abstract":"In this demo, we present a Virtual Reality (VR) Prototype that assists geoscientist in the task of seismic interpretation. The system renders a 3D seismic volume in a virtual reality environment where users may see semantic information and add annotations. The data integration is provided by a hybrid knowledge base that handles multimodal data like 3D models and multimedia content. The knowledge base can support other systems as well, which permits reasoning over the data. Therefore, our proposed system is intended to assist users in seismic interpretation by combining visual inspection with immersion, semantic information retrieval, and structured storage.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125522607","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}
3D motion capture of human movement in animation and biomechanics has developed in relatively separate and parallel domains. The two disciplines use different language, software, computational models and have different aims. As a result, in the life sciences, human movement is predominantly analyzed as non-visual biomechanical data. Whereas human movement visualization in animation typically lacks the accuracy outside of that required in the entertainment industry. This project draws from both disciplines to develop a novel approach in the creation of participant specific, motion capture skeletons which are retargeted onto participant specific, anatomically scaled, humanoid avatars. The customized motion capture marker placement, skeleton and character scaling used in this new approach aims to retain a high level of movement fidelity and minimize discrepancies between participant and avatar movement. This process has been used in the visualization of aesthetic movement such as dance and provides a step towards the generation of a digital double which can facilitate full body immersion into digital environments.
{"title":"Integrating Biomechanical and Animation Motion Capture Methods in the Production of Participant Specific, Scaled Avatars","authors":"L. Hopper, Nahoko Sato","doi":"10.1109/AIVR.2018.00054","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00054","url":null,"abstract":"3D motion capture of human movement in animation and biomechanics has developed in relatively separate and parallel domains. The two disciplines use different language, software, computational models and have different aims. As a result, in the life sciences, human movement is predominantly analyzed as non-visual biomechanical data. Whereas human movement visualization in animation typically lacks the accuracy outside of that required in the entertainment industry. This project draws from both disciplines to develop a novel approach in the creation of participant specific, motion capture skeletons which are retargeted onto participant specific, anatomically scaled, humanoid avatars. The customized motion capture marker placement, skeleton and character scaling used in this new approach aims to retain a high level of movement fidelity and minimize discrepancies between participant and avatar movement. This process has been used in the visualization of aesthetic movement such as dance and provides a step towards the generation of a digital double which can facilitate full body immersion into digital environments.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122631723","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}
Brandon Huynh, Adam Ibrahim, YunSuk Chang, Tobias Höllerer, J. O'Donovan
Augmented Reality interfaces increasingly utilize artificial intelligence systems to tailor content and experiences to the user. We explore the effects of one such system - a recommender system for online shopping - which allows customers to view personalized product recommendations in the physical spaces where they might be used. We describe results of a 2x3 condition exploratory study in which recommendation quality was varied across 3 user interface types. Our results highlight potential differences in user perception of the recommended objects in an AR environment. Specifically, users rate product recommendations significantly higher in AR and in a 3D browser interface, and show a significant increase in trust in the recommender system, compared to a web interface with 2D product images. Through semi-structured interviews, we gather participant feedback which suggests AR interfaces perform better due to their ability to view products within the physical context where they will be used.
{"title":"A Study of Situated Product Recommendations in Augmented Reality","authors":"Brandon Huynh, Adam Ibrahim, YunSuk Chang, Tobias Höllerer, J. O'Donovan","doi":"10.1109/AIVR.2018.00013","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00013","url":null,"abstract":"Augmented Reality interfaces increasingly utilize artificial intelligence systems to tailor content and experiences to the user. We explore the effects of one such system - a recommender system for online shopping - which allows customers to view personalized product recommendations in the physical spaces where they might be used. We describe results of a 2x3 condition exploratory study in which recommendation quality was varied across 3 user interface types. Our results highlight potential differences in user perception of the recommended objects in an AR environment. Specifically, users rate product recommendations significantly higher in AR and in a 3D browser interface, and show a significant increase in trust in the recommender system, compared to a web interface with 2D product images. Through semi-structured interviews, we gather participant feedback which suggests AR interfaces perform better due to their ability to view products within the physical context where they will be used.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128703688","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}
Simon M. Hofmann, Felix Klotzsche, A. Mariola, V. Nikulin, A. Villringer, Michael Gaebler
Emotional arousal (EA) denotes a heightened state of activation that has both subjective and physiological aspects. The neurophysiology of subjective EA, among other mind-brain-body phenomena, can best be tested when subjects are stimulated in a natural fashion. Immersive virtual reality (VR) enables naturalistic experimental stimulation and thus promises to increase the ecological validity of research findings i.e., how well they generalize to real-life settings. In this study, 45 participants experienced virtual rollercoaster rides while their brain activity was recorded using electroencephalography (EEG). A Long Short-Term Memory (LSTM) recurrent neural network (RNN) was then trained on the alpha-frequency (8-12 Hz) component of the EEG signal (input) and the retrospectively acquired continuous reports of subjective EA (target). With the LSTM-based model, subjective EA could be predicted significantly above chance level. This demonstrates a novel EEG-based decoding approach for subjective states of experience in naturalistic research designs using VR.
{"title":"Decoding Subjective Emotional Arousal during a Naturalistic VR Experience from EEG Using LSTMs","authors":"Simon M. Hofmann, Felix Klotzsche, A. Mariola, V. Nikulin, A. Villringer, Michael Gaebler","doi":"10.1109/AIVR.2018.00026","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00026","url":null,"abstract":"Emotional arousal (EA) denotes a heightened state of activation that has both subjective and physiological aspects. The neurophysiology of subjective EA, among other mind-brain-body phenomena, can best be tested when subjects are stimulated in a natural fashion. Immersive virtual reality (VR) enables naturalistic experimental stimulation and thus promises to increase the ecological validity of research findings i.e., how well they generalize to real-life settings. In this study, 45 participants experienced virtual rollercoaster rides while their brain activity was recorded using electroencephalography (EEG). A Long Short-Term Memory (LSTM) recurrent neural network (RNN) was then trained on the alpha-frequency (8-12 Hz) component of the EEG signal (input) and the retrospectively acquired continuous reports of subjective EA (target). With the LSTM-based model, subjective EA could be predicted significantly above chance level. This demonstrates a novel EEG-based decoding approach for subjective states of experience in naturalistic research designs using VR.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129304774","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}
{"title":"IEEE AIVR 2018 Technical Program Committee Members and Reviewers","authors":"","doi":"10.1109/aivr.2018.00008","DOIUrl":"https://doi.org/10.1109/aivr.2018.00008","url":null,"abstract":"","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123356437","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}
The reconstruction and visualization of threedimensional point-cloud models, obtained by terrestrial laser scanners, is interesting to many research areas. This paper presents an algorithm to decimate redundant information in realworld indoor point-cloud scenes. The key idea is to recognize planar segments from the point-cloud and to decimate their inlier points by the triangulation of the boundary, describing the shape. To achieve this RANSAC, normal vector filtering, statistical clustering, alpha shape boundary recognition and the constrained Delaunay triangulation are used. The algorithm is tested on various large dense point-clouds and is capable of reduction rates from approximately 75-95%.
{"title":"Planar Simplification of Indoor Point-Cloud Environments","authors":"Stephan Feichter, H. Hlavacs","doi":"10.1109/AIVR.2018.00066","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00066","url":null,"abstract":"The reconstruction and visualization of threedimensional point-cloud models, obtained by terrestrial laser scanners, is interesting to many research areas. This paper presents an algorithm to decimate redundant information in realworld indoor point-cloud scenes. The key idea is to recognize planar segments from the point-cloud and to decimate their inlier points by the triangulation of the boundary, describing the shape. To achieve this RANSAC, normal vector filtering, statistical clustering, alpha shape boundary recognition and the constrained Delaunay triangulation are used. The algorithm is tested on various large dense point-clouds and is capable of reduction rates from approximately 75-95%.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126220575","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}
In this paper, a controlled natural language (CNL) based program synthesis system for the Lego Mindstorms EV3 (EV3) is introduced. The system is developed with the intention of helping middle and high school Lego robotics enthusiasts and non-programmers to learn the necessary skills for programming and engineering the robot with less effort. The system generates the resulting code in Microsoft Small Basic that controls the EV3 Intelligent Brick with supports for all EV3 sensors and motors. Preliminary results show that our approach is capable of generating functional, executable code based on the users' controlled natural language specifications. Detailed error messages are also given when confronted with unimplementable sentences.
{"title":"A Natural Language Programming Application for Lego Mindstorms EV3","authors":"Yue Zhan, M. Hsiao","doi":"10.1109/AIVR.2018.00012","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00012","url":null,"abstract":"In this paper, a controlled natural language (CNL) based program synthesis system for the Lego Mindstorms EV3 (EV3) is introduced. The system is developed with the intention of helping middle and high school Lego robotics enthusiasts and non-programmers to learn the necessary skills for programming and engineering the robot with less effort. The system generates the resulting code in Microsoft Small Basic that controls the EV3 Intelligent Brick with supports for all EV3 sensors and motors. Preliminary results show that our approach is capable of generating functional, executable code based on the users' controlled natural language specifications. Detailed error messages are also given when confronted with unimplementable sentences.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"40 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132241512","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}
Chun-Ming Chang, Wolfgang Huerst, Xiaojuan Ma, Alexander Plopski, Klen Copic Pucihar, A. E. Saddik, Vida Groznik, Min-Chun Hu, M. Kljun, Zerrin Yumak, João Ascenso, R. Capobianco, Guido, D. Iwai, F. Sandnes, H. Schuldt, M. Sert, Jarno Vanne, Rong-Ming Chen, P. Sheu, J. Tsai
Research in Virtual Reality (VR) is concerned with computing technologies that allow humans to see, hear, talk, think, learn, and solve problems in virtual and augmented environments. Research in Artificial Intelligence (AI) addresses technologies that allow computing machines to mimic these same human abilities. Although these two fields evolved separately, they share an interest in human senses, skills, and knowledge production. Thus, bringing them together will enable us to create more natural and realistic virtual worlds and develop better, more effective applications. Ultimately, this will lead to a future in which humans and humans, humans and machines, and machines and machines are interacting naturally in virtual worlds, with use cases and benefits we are only just beginning to imagine.
{"title":"Message from the IEEE AIVR 2018 General Co-Chairs","authors":"Chun-Ming Chang, Wolfgang Huerst, Xiaojuan Ma, Alexander Plopski, Klen Copic Pucihar, A. E. Saddik, Vida Groznik, Min-Chun Hu, M. Kljun, Zerrin Yumak, João Ascenso, R. Capobianco, Guido, D. Iwai, F. Sandnes, H. Schuldt, M. Sert, Jarno Vanne, Rong-Ming Chen, P. Sheu, J. Tsai","doi":"10.1109/aivr.2018.00005","DOIUrl":"https://doi.org/10.1109/aivr.2018.00005","url":null,"abstract":"Research in Virtual Reality (VR) is concerned with computing technologies that allow humans to see, hear, talk, think, learn, and solve problems in virtual and augmented environments. Research in Artificial Intelligence (AI) addresses technologies that allow computing machines to mimic these same human abilities. Although these two fields evolved separately, they share an interest in human senses, skills, and knowledge production. Thus, bringing them together will enable us to create more natural and realistic virtual worlds and develop better, more effective applications. Ultimately, this will lead to a future in which humans and humans, humans and machines, and machines and machines are interacting naturally in virtual worlds, with use cases and benefits we are only just beginning to imagine.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132473916","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}
In this paper, we consider a human-AI collaboration task, fashion design, in augmented reality environment. In particular, we propose a compensation method of two-stage image generation neural network for generating fashion design with progressive users' inputs. Our work is based on a recent proposed deep learning model, pix2pix, that can successfully transform an image from one domain into another domain, such as from line drawings to color images. However, the pix2pix model relies on the condition that input images should come from the same distribution, which is usually hard for applying it to real humancomputer interaction tasks, where the input from users differs from individual to individual. To address the problem, we propose a compensation method of two-stage image generation. In the first stage, we ask users to indicate their design preference with an easy task, such as tuning clothing landmarks, and use the input to generate a compensation input. With the compensation input, in the second stage, we then concatenate it with the real sketch from users to generate a perceptual better result. In addition, to deploy the two-stage image generation neural network in augmented reality environment, we designed and implemented a mobile application where users can create fashion design referring to real world human models. With the augmented 2D screen and instant feedback from our system, users can design clothing by seamlessly mixing the real and virtual environment. Through an online experiment with 46 participants and an offline use case study, we showcase the capability and usability of our system. Finally, we discuss the limitations of our system and further works on human-AI collaborated design.
{"title":"A Compensation Method of Two-Stage Image Generation for Human-AI Collaborated In-Situ Fashion Design in Augmented Reality Environment","authors":"Zhenjie Zhao, Xiaojuan Ma","doi":"10.1109/AIVR.2018.00018","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00018","url":null,"abstract":"In this paper, we consider a human-AI collaboration task, fashion design, in augmented reality environment. In particular, we propose a compensation method of two-stage image generation neural network for generating fashion design with progressive users' inputs. Our work is based on a recent proposed deep learning model, pix2pix, that can successfully transform an image from one domain into another domain, such as from line drawings to color images. However, the pix2pix model relies on the condition that input images should come from the same distribution, which is usually hard for applying it to real humancomputer interaction tasks, where the input from users differs from individual to individual. To address the problem, we propose a compensation method of two-stage image generation. In the first stage, we ask users to indicate their design preference with an easy task, such as tuning clothing landmarks, and use the input to generate a compensation input. With the compensation input, in the second stage, we then concatenate it with the real sketch from users to generate a perceptual better result. In addition, to deploy the two-stage image generation neural network in augmented reality environment, we designed and implemented a mobile application where users can create fashion design referring to real world human models. With the augmented 2D screen and instant feedback from our system, users can design clothing by seamlessly mixing the real and virtual environment. Through an online experiment with 46 participants and an offline use case study, we showcase the capability and usability of our system. Finally, we discuss the limitations of our system and further works on human-AI collaborated design.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132516525","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 discusses a VR-based system that aims to support professionals of the Oil & Gas Industry in interpreting seismic data. Seismic interpretation plays an important role in decision making prior to oil exploration. Part of the seismic interpretation process consists in visualizing slices from a volume generated by a seismograph and looking for specific patterns and features. In this work, we take this volume and render it in a VR environment. Our system integrates with a knowledge base to better support the decision-making process. With such an integration, experts can explore the 3D volume of a given seismic cube and spatially visualize semantic information of that area that is stored in the knowledge base. Therefore, our proposed system is intended to assist users in the whole process by combining visual inspection with immersion, semantic information retrieval, and structured storage.
{"title":"Exploring Seismic Data through Virtual Reality and Hybrid Knowledge Base","authors":"W. Santos, Reinaldo Silva, R. Santos, M. Moreno","doi":"10.1109/AIVR.2018.00038","DOIUrl":"https://doi.org/10.1109/AIVR.2018.00038","url":null,"abstract":"This paper discusses a VR-based system that aims to support professionals of the Oil & Gas Industry in interpreting seismic data. Seismic interpretation plays an important role in decision making prior to oil exploration. Part of the seismic interpretation process consists in visualizing slices from a volume generated by a seismograph and looking for specific patterns and features. In this work, we take this volume and render it in a VR environment. Our system integrates with a knowledge base to better support the decision-making process. With such an integration, experts can explore the 3D volume of a given seismic cube and spatially visualize semantic information of that area that is stored in the knowledge base. Therefore, our proposed system is intended to assist users in the whole process by combining visual inspection with immersion, semantic information retrieval, and structured storage.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128952287","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：