March 18, 2013

Talk by Vladimr Kim

Title: Discovering Similarities In Diverse Collections of 3D Shapes

Abstract:

Due to recent developments in modeling software and advances in acquisition techniques for 3D geometry, large numbers of shapes have been digitized. Existing datasets include millions of real-world objects, cultural heritage artifacts, scientific and engineering models. As large repositories of 3D shape collections continue to grow, understanding the data, especially the inter-model similarity and geometric variations across models, is essential for effective organization, exploration and analysis of these datasets.

In this talk, I will describe a novel method for computing per-point correspondences across all shapes in a geometrically diverse collection. A traditional solution to this problem is to align pairs of shapes independently, which is inefficient and does not leverage transitivity of correspondences. We address these challenges with a method based on diffusion maps. Our algorithm robustly aligns diverse shapes and produces correspondences for the whole collection using just a subset of pairwise maps. We evaluate our algorithm on correspondence benchmarks and report substantial improvement over previous methods. Finally, we demonstrate that our analysis enables interactive exploration of 3D collections based on similarities and differences between shapes in user-specified regions of interest. 

Bio:

Vladimir G. Kim is a Ph.D. candidate (June 2013) in the Computer Science Department at Princeton University. The main focus of his graduate research has been structural analysis of 3D geometries, including computing correspondences between shapes, symmetry detection, and object recognition. He spent summers of 2011 and 2012 as a research intern at Adobe Systems. He received his B.A. degree (with Honours) in Mathematics and Computer Science from Simon Fraser University in 2008.

Vladimir is a recipient of the Siebel Scholarship (Class of 2013) which is awarded annually for academic excellence and demonstrated leadership to 85 top students from the world's leading graduate schools. His graduate studies are also supported by the NSERC Postgraduate Scholarship and a Princeton Graduate Fellowship. 

Website: http://www.cs.princeton.edu/~vk/