Data Science Warsaw #40 AR & SLAM

On Monday, 24th September, we'll have two talks at Data Science Warsaw Meetup and then the After Party powered by NETHONE! This time we would also like to thank Tooploox for help in inviting such great speakers.

1. Augmented reality with Google ARCore, Jacek Komorowski, Ph.D.

Abstract: In this presentation, I’ll talk about the collaboration between Warsaw University of Technology and Google on the development of the Google ARCore (formerly known as Google Tango) augmented reality solution. I’ll explain key elements of an augmented reality solution for mobile devices. How the mobile device tracks its position and orientation relative to the real world? How the virtual content is blended with a real world seen by the phone’s camera? I’ll also discuss some of the problems encountered during the development of an augmented reality solution.

Bio: Jacek Komorowski is an Assistant Professor in the Division of Computer Graphics in the Institute of Computer Science at Warsaw University of Technology. He also works as AI Expert in Sport Algorithmics and Gaming, developing computer vision and machine learning solutions to automate the analysis of sport videos. His Ph. D. focused on face recognition based on 3D face model reconstructed from a series of images. His research interests include computer vision, machine learning and augmented reality.

2. Learning Deep Convolutional Frontends for Visual SLAM, Tomasz Malisiewicz, PhD

Abstract: A broad range of robotics and mixed reality systems are built on top of traditional Simultaneous Localization and Mapping (SLAM) algorithms. This talk will discuss the frontend/backend distinction in SLAM as well as discuss our group’s recent research on ConvNet-based frontends for Visual SLAM. The talk will focus on Deep Learning architectures for geometric computer vision tasks as well as novel self-supervised methods of training such networks when ground-truth training data is difficult/impossible to obtain.

Bio: Tomasz is a Principal Engineer at Magic Leap, focusing on applied research at the intersection of Deep Learning, SLAM, and Mixed Reality. He obtained his PhD from Carnegie Mellon’s Robotics Institute in 2011 under the supervision of Alexei A. Efros, spent two years as a postdoctoral researcher at MIT CSAIL, and co-founded a small computer vision startup in Boston. Originally from Włocławek, Poland, Tomasz currently lives and works in sunny Mountain View, California.

Talk Keywords: Perception for Mixed Reality, Visual SLAM, Descriptor Learning, Self-Supervised Learning, Fully-convolutional ConvNets, Geometric Deep Learning
Relevant Links:
SuperPoint Research Paper: https://arxiv.org/abs/1712.07629
SuperPoint Network Release: https://github.com/MagicLeapResearch/SuperPointPretrainedNetwork

After the meetup, we invite you to the AfterParty sponsored by Nethone - a Polish company that provides AI-based anti-fraud and Business Intelligence solutions for online merchants. More about Nethone http://www.nethone.com
FB: @NethoneAI https://www.facebook.com/NethoneAI/,
TT: @Nethone_ https://twitter.com/Nethone_,
Li: Nethone https://www.linkedin.com/company/nethone

We also encourage you to subscribe to the newsletter (https://tinyletter.com/datascience), where we inform about interesting events regarding Data Science in Warsaw and in Poland.