3D Shape Sequence of Human Comparison and Classification using Current and Varifolds

TL;DR

This paper introduces a novel method for comparing and classifying 3D human shape sequences by embedding them in the space of varifolds and using Gram-Hankel matrices, effectively handling motion dynamics and surface parametrization changes.

Contribution

The paper proposes a new approach that embeds 3D shape sequences into varifold space and uses Gram-Hankel matrices for comparison, addressing challenges of motion dynamics and parametrization invariance.

Findings

Method is competitive with state-of-the-art in 3D human motion retrieval.

Embedding in varifold space provides invariance to rigid motions and parametrization.

Experiments on CVSSP3D and Dyna datasets validate effectiveness.

Abstract

In this paper we address the task of the comparison and the classification of 3D shape sequences of human. The non-linear dynamics of the human motion and the changing of the surface parametrization over the time make this task very challenging. To tackle this issue, we propose to embed the 3D shape sequences in an infinite dimensional space, the space of varifolds, endowed with an inner product that comes from a given positive definite kernel. More specifically, our approach involves two steps: 1) the surfaces are represented as varifolds, this representation induces metrics equivariant to rigid motions and invariant to parametrization; 2) the sequences of 3D shapes are represented by Gram matrices derived from their infinite dimensional Hankel matrices. The problem of comparison of two 3D sequences of human is formulated as a comparison of two Gram-Hankel matrices. Extensive experiments on CVSSP3D and Dyna datasets show that our method is competitive with state-of-the-art in 3D human sequence motion retrieval. Code for the experiments is available at https://github.com/CRISTAL-3DSAM/HumanComparisonVarifolds.