3D Point Cloud Classification, Segmentation and Normal (...) - Lindenbaum - Workshop 2 - CEB T1 2019

Michael Lindenbaum (Technion) / 12.03.2019 3D Point Cloud Classification, Segmentation and Normal estimation, using 3D Modified Fisher Vector Representation and Convolutional Neural Networks. The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods. The common solution of transforming the data into a 3D voxel grid introduces its own challenges, mainly large memory size. We propose a novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV). Our representation is hybrid and combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way. Using the grid enables us to design a new CNN architecture for point cloud classification and part segmentation. In a series of experiments we demonstrate excellent performance in the tasks of classification, part segmentation, and normal estimation. Joint work with Yizhak Ben-Shabat and Anath Fischer. ---------------------------------- Vous pouvez nous rejoindre sur les réseaux sociaux pour suivre nos actualités. Facebook : https://www.facebook.com/InstitutHenriPoincare/ Twitter : https://twitter.com/InHenriPoincare Instagram : https://www.instagram.com/instituthenripoincare/ ************************************* Langue : Anglais; Date : 12.03.2019; Conférencier : Lindenbaum, Michael; Évenement : Workshop 2 - CEB T1 2019; Lieu : IHP; Mots Clés : point clouds, 3D Modified Fisher Vectors (3DmFV), CNN, point cloud classification, part segmentation, normal estimation