Department of Computer Engineering
S E M I N A R
Learning 3D Representations with Capsules & Beyond
Dr. Tolga Birdal
Stanford University, USA
3D data is arguably the most expressive digital storage for the real physical objects around us. However, it has been repeatedly shown that a flat grid, such as the pixels underlying 2D images, may not be the best encoding for many applications. This brings an additional challenge to 3D machine learning, namely deducing useful and faithful representations from the raw input. In fact, learning expressive and capable representations with adequate abstraction, generation and generalization power is a perennial challenge. In this series of works, Tolga Birdal will make a case for the capsule networks as a way of summarizing 3D data to enable multitudes of applications ranging from segmentation to part interpolation and pose estimation. Methods and findings related to this talk have been published in CVPR'19, ECCV'20 besides the works under review. These papers can be found under the following links respectively: https://arxiv.org/abs/1812.10775, https://arxiv.org/abs/1912.12098.
Bio: Tolga Birdal is a Postdoctoral Research Fellow at Stanford University. He carries his research within the Geometric Computing Group of Prof. Leonidas Guibas. Previously, Tolga has defended his PhD thesis at the Computer Vision Group, Chair for Computer Aided Medical Procedures, Technical University of Munich led by Prof. Nassir Navab. He was also a Doktorand at Siemens AG. Tolga completed his Bachelors as an Electronics Engineer at Sabanci University in 2008. In his subsequent postgraduate programme, he studied Computational Science and Engineering at Technical University of Munich. In continuation to his Master's thesis on "3D Deformable Surface Recovery Using RGBD Cameras", he focused his research and development on large object detection, pose estimation and reconstruction using point clouds. Tolga is awarded both Ernst von Siemens Scholarship and EMVA Young Professional Award 2016 for his PhD work. He has several publications at the well respected venues such as NeurIPS, CVPR, ICCV, ECCV, IROS, ICASSP and 3DV. Aside from his academic life, Tolga is a natural Entrepreneur. He has co-founded multiple companies including Befunky, a widely used web based image processing platform. For further information, visit tbirdal.me , https://profiles.stanford.edu/tolga-birdal.
DATE: 01 April 2021, Thursday @ 09:00