BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes
This work addresses the challenge of handling unregistered human body scans for applications like motion transfer and shape generation, offering a novel framework that is incremental in its approach.
The authors tackled the problem of representing, interpolating, and extrapolating human body shapes from unregistered meshes without requiring point-to-point correspondences, achieving significant improvements in shape registration, interpolation, and extrapolation on the FAUST and DFAUST datasets.
We present Basis Restricted Elastic Shape Analysis (BaRe-ESA), a novel Riemannian framework for human body scan representation, interpolation and extrapolation. BaRe-ESA operates directly on unregistered meshes, i.e., without the need to establish prior point to point correspondences or to assume a consistent mesh structure. Our method relies on a latent space representation, which is equipped with a Riemannian (non-Euclidean) metric associated to an invariant higher-order metric on the space of surfaces. Experimental results on the FAUST and DFAUST datasets show that BaRe-ESA brings significant improvements with respect to previous solutions in terms of shape registration, interpolation and extrapolation. The efficiency and strength of our model is further demonstrated in applications such as motion transfer and random generation of body shape and pose.