Pose-Oblivious Shape Signature

Abstract

A 3D shape signature is a compact representation for some essence of a shape. Shape signatures are commonly utilized as a fast indexing mechanism for shape retrieval. Effective shape signatures capture some global geometric properties which are scale, translation, and rotation invariant. In this paper, we introduce an effective shape signature which is also pose-oblivious. This means that the signature is also insensitive to transformations which change the pose of a 3D shape such as skeletal articulations. Although some topology-based matching methods can be considered pose-oblivious as well, our new signature retains the simplicity and speed of signature indexing. Moreover, contrary to topology-based methods, the new signature is also insensitive to the topology change of the shape, allowing us to match similar shapes with different genus. Our shape signature is a 2D histogram which is a combination of the distribution of two scalar functions defined on the boundary surface of the 3D shape. The first is a definition of a novel function called the local-diameter function. This function measures the diameter of the 3D shape in the neighborhood of each vertex. The histogram of this function is an informative measure of the shape which is insensitive to pose changes. The second is the centricity function that measures the average geodesic distance from one vertex to all other vertices on the mesh. We evaluate and compare a number of methods for measuring the similarity between two signatures, and demonstrate the effectiveness of our pose-oblivious shape signature within a 3D search engine application for different databases containing hundreds of models.

Heat-mapping: A robust approach toward perceptually consistent mesh segmentation

“…The readers are referred to [2,7,24,19,27,21] about general mesh segmentation approaches. The importance of the PCMS has been highlighted in some recent works [8,16,23,25,11] .…”

“…We carry out two sets of tests on the centaur model and the armadillo model. The models used in the experiments were chosen from the following databse: ISDB, Princeton Shape Benchmark for 3D Segmentation and TOSCA nonrigid world 3D database [11,7,5,4,6].…”

Model Composition from Interchangeable Components

“…Several methods do this by matching models skeletons [24,5] or feature vertices [9]. Others compute complete point-to-point correspondences [2,14,8]. Most feature based methods are robust only under rigid transformations.…”

“…Global point-to-point correspondence methods are closest to the task we address, and successfully find maps between models within the same class. The more recent methods [14,8,2] correctly map major features, however the mapping they provide may not map the natural part boundaries in a consistent manner and thus may not always preserve the geometric meaning of the parts. These methods operate on watertight models and thus cannot be used on many available models of man-made objects, such as chairs, which contain multiple connected components.…”

Correspondence labelling for wide-timeframe free-form surface matching

“…Local feature descriptors have been developed for 3D shape matching in 3D shape recognition [9]. Gal et al [6] introduce a local shape distribution descriptor that is invariant to articulated pose. Gatzke and Garland [7] resample surface curvature onto a radial descriptor embedded on the surface.…”