A Non-structural Representation Scheme for Articulated Shapes
This provides an alternative approach for shape analysis in computer vision, but it is incremental as it matches existing methods without surpassing them.
The paper tackles the problem of representing articulated shapes without structural models by proposing a pixel-based distinctness measure and region assignment for similarity, achieving clustering results comparable to state-of-the-art methods on three datasets.
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.