COMPACT PART-BASED SHAPE SPACES FOR DENSE CORRESPONDENCES

OLIVER BURGHARD, ALEXANDER BERNER, MICHAEL WAND, NILOY MITRA, HANS-PETER SEIDEL,REINHARD KLEIN

(a) shape collection
(b) coarse segmentation
(c) dense correspondences

Abstract

We consider the problem of establishing dense correspondences
within a set of related shapes of strongly varying geometry. For such input,
traditional shape matching approaches often produce unsatisfactory results.
We propose an ensemble optimization method that improves given coarse correspondences
to obtain dense correspondences. Following ideas from minimum
description length approaches, it maximizes the compactness of the induced
shape space to obtain high-quality correspondences. We make a number of
improvements that are important for computer graphics applications: Our approach
handles meshes of general topology and handles partial matching between
input of varying topology. To this end we introduce a novel part-based
generative statistical shape model. We develop a novel analysis algorithm that
learns such models from training shapes of varying topology. We also provide a
novel synthesis method that can generate new instances with varying part layouts
and subject to generic variational constraints. In practical experiments,
we obtain a substantial improvement in correspondence quality over state-ofthe-
art methods. As example application, we demonstrate a system that learns
shape families as assemblies of deformable parts and permits real-time editing
with continuous and discrete variability.

Correspondences Result

Samping Results