Ingredients for Mapping the Metaverse
Join us for our upcoming Future Computing Seminar Series
Speaker: Dr. Peter Kontschieder, Director - Research Science, Meta Reality Labs Zurich
Date: April 23rd, 2024, 15:00 CET
Where: ETZ H 91 & external page Online
Abstract:
In this talk, I will discuss some of our recent research directions for obtaining photorealistic, 3D replica of environments based on data captured in the wild. Our grand goal is to generate representations that are indistinguishable from the real world in terms of visual fidelity, while enabling us to escape the laws of physics and providing truly immersive and magical experiences in VR. My presentation will discuss our group's research findings in the domains of classical and modern CV/ML/CG, providing the basic ingredients for mapping the Metaverse. More specifically, I will talk about our recent works in the context of neural 3D reconstruction and rendering, semantic scene understanding, and how to handle imperfections due to data captured with commodity cameras.
Speaker Bio:
Peter Kontschieder received his PhD in 2013 from Graz University of Technology and is currently a Director (Research Science) at Meta Reality Labs in Zurich. His research interests include computer vision and machine learning, with particular focus on neural 3D scene modeling, semantic scene understanding, image-based 3D modeling, and generative models for 3D synthesis. From 2013-2016 he was a postdoctoral researcher in the Machine Intelligence and Perception group at Microsoft Research in Cambridge (UK). In 2016 he joined Mapillary and founded Mapillary Research – Mapillary's research group focusing on applied research in Computer Vision and Machine Learning. With the acquisition of Mapillary in 2020, Peter and his team joined Facebook in Zurich. Peter received the Marr Prize in 2015 for his contribution of Deep Neural Decision Forests, joining deep learning with decision forests. He co-organized several tutorials and workshops on object recognition and robust computer vision at major conferences like CVPR, ECCV, and ICCV. He regularly published his research in high-impact conferences like ICCV, CVPR, ECCV, NeurIPS, ICML and IJCAI.