Doctoral Consortium Session 1 Platinum Pass Full Conference Pass Full Conference One-Day Pass Basic Conference Pass Student One-Day Pass Date: Sunday, November 17th Time: 9:00am - 11:00am Venue: Plaza Meeting Room P2 Extended Reality Experiences Prediction using Collaborative Filtering Speaker(s): Irene M. Gironacci, Swinburne University of Technology, Australia Description: Extended Reality applications and simulators are increasingly becoming popular in business, but are often limited by their predictability and moreover, they lack personalization. The author proposes the usage of recommendation systems in extended reality simulators to solve this problem, through a platform in which extended reality experiences are suggested to the user using an item-based collaborative filtering approach with a precision of 71%. KNN is used to find clusters of similar items based on item similarity and user’s ratings. This platform leads to a new generation of smart simulators and can be highly valuable for personalized professional training and entertainment. Bio of Speaker: Irene M. Gironacci is a Software Engineer and she is currently working as Project Manager at Swinburne University of Technology. She is also currently working towards the PhD and Graduate Certificate in Research and Innovation Management at the same university. Her research interests include Extended Reality, Artificial Intelligence, Game Design and Management. Previously, she worked as Mixed Reality Engineer on a H2020 project at Luxembourg Institute of Science and Technology. She has further experience as Scrum Master, and R&D Consultant. She received both MSc and BSc in Software Engineering at University of Parma. Contact her at email@example.com or firstname.lastname@example.org (www.imgportal.net). Material acquisition using deep learning Speaker(s): Valentin Deschaintre, Ansys; Université Cote d'Azur, Inria, France Description: Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in pictures. Designing algorithms able to leverage these cues to recover spatially-varying bi-directional reflectance distribution functions (SVBRDFs) from a few images has challenged computer graphics researchers for decades. I explore the use of deep learning to tackle lightweight appearance capture and make sense of these visual cues. We introduce several innovations on training data acquisition and network design, bringing clear improvement over the state of the art for lightweight material capture using as little as one picture and up to 10 images. Bio of Speaker: Valentin is a 3rd year PhD student at Inria in Sophia Antipolis with the GraphDeco group under the supervision on Adrien Bousseau and George Drettakis. During his PhD he spent 2 months in MIT under the supervision of Fredo Durand. His research focuses on material acquisition and representation, with a particular interest in deep learning methods. His PhD is funded with the CIFRE system by ANRT and Optis , an Ansys affiliate. Numerical Linear Algebra for physically-based Fluid Animations Speaker(s): Tim Krake, University of Stuttgart; Hochschule der Medien, Stuttgart, Germany Description: The investigation of simulations by mathematical techniques give a revealing insight into hidden structures: For physically-based fluid animations, the use of (matrix) decomposition methods based on spectral theory leads to both theoretical insights and practical enhancements of the algorithm in terms of precision, efficiency, and stability. Bio of Speaker: Tim Krake is a PhD student at the Visualization Research Center, University of Stuttgart and at the Hochschule der Medien, Stuttgart, where he is a member of the joint graduate school Digital Media. He is currently working on the integration of mathematical techniques (mainly based on decomposition methods) to the field of computer graphics and visualization. In this context, his particular interest is the simulation of physically-based fluids. He received both his MSc and his BSc in mathematics at the University of Tuebingen. Virtual Reality in the Art Museum: A Review of Debates and Proposition of a Theoretical Approach Speaker(s): Hao Zhou, UNSW Art & Design, Australia Description: This research seeks to explore an integrated, situational approach based on the notion of presence to investigate the use of Virtual Reality in the art museum, by incorporating multiple theories and perspectives in related fields, findings from practical projects as case studies as well as insights from practitioners. Bio of Speaker: Hao Zhou is currently a PhD candidate at UNSW Art & Design. With a background in both science and design as well as experiences in other fields, Hao adopts an inter-disciplinary approach in his research. He is interested in the transforming impacts of new technologies in the contemporary sociocultural context. In his ongoing PhD, he investigates the use of Virtual Reality in the art museum, which seeks to develop an integrated approach to inspect the complex issues involved by drawing on multiple theories and perspectives derived from a central notion of ‘presence’.