A Non-structural Representation Scheme for Articulated Shapes

TL;DR

This paper introduces a pixel-based, non-structural shape representation and similarity measure for articulated shapes, enabling effective clustering without explicit modeling of part relations.

Contribution

It proposes a novel pixel-based shape representation and similarity measure that does not rely on structural models like graphs or trees.

Findings

Performs comparably to state-of-the-art graph-based methods

Effective in clustering articulated shapes without explicit structural modeling

Uses Hungarian algorithm for shape region matching

Abstract

For representing articulated shapes, as an alternative to the structured models based on graphs representing part hierarchy, we propose a pixel-based distinctness measure. Its spatial distribution yields a partitioning of the shape into a set of regions each of which is represented via size normalized probability distribution of the distinctness. Without imposing any structural relation among parts, pairwise shape similarity is formulated as the cost of an optimal assignment between respective regions. The matching is performed via Hungarian algorithm permitting some unmatched regions. The proposed similarity measure is employed in the context of clustering a set of shapes. The clustering results obtained on three articulated shape datasets show that our method performs comparable to state of the art methods utilizing component graphs or trees even though we are not explicitly modeling component relations.