Technical Papers

Shape Sets and Trees

Friday, 30 November 11:00 - 13:00 |  Peridot 201

Active Co-Analysis of a Set of Shapes - Picture

Active Co-Analysis of a Set of Shapes

We present a semi-supervised learning method for the co-analysis of sets of shapes. We show the effectiveness of this method as a means to quickly converge towards an error-free consistent part labeling.


Yunhai Wang, Shenzhen Institutes of Advanced Technology
Shmulik Asafi, Tel Aviv University
Oliver van Kaick, Simon Fraser University
Hao (Richard) Zhang, Simon Fraser University
Daniel Cohen-Or, Tel Aviv University
Baoquan Chen, Shenzhen Institutes of Advanced Technology


Co-Abstraction of Shape Collections - Picture

Co-Abstraction of Shape Collections

We present a co-abstraction method that takes as input a collection of shapes, and produces a mutually consistent and individually identity-preserving abstraction of each shape. We hierarchically generate a spectrum of abstractions for each model in a collection, and then compute the appropriate abstraction level for each model.


Mehmet Ersin Yumer, Carnegie Mellon University
Levent Burak Kara, Carnegie Mellon University


An Optimization Approach for Extracting and Encoding Consistent Maps - Picture

An Optimization Approach for Extracting and Encoding Consistent Maps

We introduce a novel approach that takes as input a sparse set of imperfect initial maps between a collection of shapes and outputs a compact data structure which implicitly encodes an improved set of maps between all pairs of shapes.


Qi-xing Huang, Stanford University
Guoxin Zhang, Tsinghua University
Lin Gao, Tsinghua University
Shimin Hu, Tsinghua University
Adrian Butscher, Stanford University
Leonidas Guibas, Stanford University


Inverse Design of Urban Procedural Models - Picture

Inverse Design of Urban Procedural Models

We propose a framework that enables adding intuitive high-level control to an existing urban procedural model. Users can specify arbitrary target indicators to control the modeling process, and our system discovers how to alter the parameters of the urban procedural model so as to produce the desired 3D output


Carlos Vanegas, University of California, Berkeley
Ignacio Garcia-Dorado, Purdue University
Daniel Aliaga, Purdue University
Bedrich Benes, Purdue University
Paul Waddell, University of California, Berkeley


Capturing and Animating the Morphogenesis of Polygonal Tree Models - Picture

Capturing and Animating the Morphogenesis of Polygonal Tree Models

Given a static tree model we present a method to compute developmental stages that approximate the tree’s natural growth. Based on structural similarity, branches are added where pruning has been applied or branches have died off over time. Furthermore, the user can explore and edit all intermediate stages.


Soeren Pirk, University of Konstanz
Till Niese, University of Konstanz
Oliver Deussen, University of Konstanz
Boris Neubert, University of Konstanz