Technical Papers

Shape Analysis

Tuesday, 23 July 2:00 PM - 3:30 PM
Session Chair: Misha Kazhdan, The Johns Hopkins University

Co-Hierarchical Analysis of Shape Structures

An unsupervised co-hierarchical analysis of a set of shapes, aimed at discovering their hierarchical part structures and revealing relations between geometrically dissimilar yet functionally equivalent shape parts across the set.

Oliver van Kaick
Simon Fraser University

Kai Xu
National University of Defense Technology

Hao Zhang
Simon Fraser University

Yanzhen Wang
National University of Defense Technology

Shuyang Sun
Simon Fraser University

Ariel Shamir
The Interdisciplinary Center Herzliya

Daniel Cohen-Or
Tel Aviv University

Learning Part-Based Templates From Large Collections of 3D Shapes

An analysis framework to derive structure from large, unorganized, diverse collections of 3D shapes. The automatic algorithm starts with an initial template model that jointly optimizes for part segmentation, point-to-point surface correspondence, and a compact deformation model to best explain the input model collection.

Vladimir Kim
Princeton University

Wilmot Li
Adobe Systems Incorporated

Niloy Mitra
University College London

Siddhartha Chaudhuri
Princeton University

Stephen DiVerdi
Adobe Systems Incorporated, Google Inc.

Thomas Funkhouser
Princeton University

Qualitative Organization of Collections of Shapes Via Quartet Analysis

This method to organize a heterogeneous collection of 3D shapes for overview and exploration applies analysis that combines several distances together into a qualitative measure. It introduces the concept of degree-of-separation charts from every shape and shows its effectiveness for exploration of interactive shapes.

Shi-Sheng Huang
Tsinghua University

Ariel Shamir
Interdisciplinary Cente Herzliya

Chao-Hui Shen
Tsinghua University

Hao Zhang
Simon Fraser University

Alla Sheffer
The University of British Columbia

Shi-Min Hu
Tsinghua University

Daniel Cohen-Or
Tel Aviv University

Map-Based Exploration of Intrinsic Shape Differences and Variability

A novel formulation of shape differences aimed at providing detailed information about the location and nature of the differences or distortions between the shapes being compared. In this method, the difference operator is much more informative than a scalar similarity score, rendering it useful in applications requiring more refined shape comparisons.

Raif Rustamov
Stanford University

Maks Ovsjanikov
École Polytechnique

Omri Azencot
Technion - Israel Institute of Technology

Mirela Ben-Chen
Technion - Israel Institute of Technology

Frederic Chazal
INRIA Saclay - Île-de-France

Leonidas Guibas
Stanford University