Elastic 3D shape analysis using square-root normal field representation

Laga, Hamid; Jermyn, Ian H.; Kurtek, Sebastian; Srivastava, Anuj

Abstract

Shape is an important physical property of natural and man-made 3D objects that characterizes their external appearances. Understanding differences between shapes, and modeling the variability within and across shape classes, hereinafter referred to as shape analysis, are problems fundamental to many applications, ranging from computer vision and computer graphics to biology and medicine. This paper provides an overview of some of the recent techniques for studying the shape of 3D objects that undergo non-rigid deformations including bending and stretching. We will mainly focus on a new representation called the square-root normal field (SRNF), discuss its properties, and show its application in the analysis of the shape of various types of objects, including human body shapes, anatomical organs such as carpal bones, and hand-drawn 2D sketches. We will show how the representation is used for (1) jointly computing correspondences and geodesics; (2) computing summary statistics such as means and modes of variations; and (3) exploring shape variability in a collection of 3D objects.

Citation

Laga, H., Jermyn, I. H., Kurtek, S., & Srivastava, A. (2017, December). Elastic 3D shape analysis using square-root normal field representation. Presented at 56th IEEE Conference on Decision and Control., Melbourne, Australia

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 56th IEEE Conference on Decision and Control.
• Start Date: Dec 12, 2017
• End Date: Dec 15, 2017
• Acceptance Date: Jul 12, 2017
• Online Publication Date: Jan 23, 2018
• Publication Date: Dec 15, 2017
• Deposit Date: Aug 9, 2017
• Publicly Available Date: Sep 18, 2017
• Publisher: Institute of Electrical and Electronics Engineers
• Pages: 2711-2717
• Book Title: 2017 IEEE 56th Annual Conference on Decision and Control (CDC) : Melbourne, Australia, 12-15 December 2017 ; proceedings.
• ISBN: 9781509028740
• DOI: https://doi.org/10.1109/cdc.2017.8264053
• Public URL: https://durham-repository.worktribe.com/output/1145845