Monday, 8 August 2:00 pm - 3:30 pm | East Building, Exhibit Hall A
Session Chair: Tom Funkhouser, Princeton University
Exploration of Continuous Variability in Collections of 3D Shapes
This paper proposes a new technique for exploring unorganized collections of 3D shapes. The approach represents the variability in the collection as a constrained deformation model of a base template shape, which the user can directly manipulate to explore the set of shapes.
Maks Ovsjanikov
Stanford University
Wilmot Li
Adobe Systems Incorporated
Leonidas Guibas
Stanford University
Niloy J. Mitra
King Abdullah University of Science and Technology
Characterizing S***ctural Relationships in Scenes Using Graph Kernels
This paper shows how to represent scenes as graphs that encode models and their semantic relationships. It then defines a kernel between these relationship graphs that compares common virtual subs***ctures in two graphs and captures the similarity between their corresponding scenes.
Matthew Fisher
Stanford University
Manolis Savva
Stanford University
Pat Hanrahan
Stanford University
Probabilistic Reasoning for Assembly-Based 3D Modeling
A probabilistic model of shape s***cture that encodes semantic and geometric relationships among shape components. The model is trained on a shape database and is used to present relevant components during interactive 3D modeling.
Siddhartha Chaudhuri
Stanford University
Evangelos Kalogerakis
Stanford University
Leonidas Guibas
Stanford University
Vladlen Koltun
Stanford University
Shape Google: Geometric Words and Expressions for Invariant Shape Retrieval
Using heat diffusion kernels as "geometric words", this technique employs the "bag of features" paradigm to cons***ct invariant shape descriptors. The descriptors provide state-of-the-art results on large-scale shape retrieval benchmarks.
Michael Bronstein