LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds

TL;DR

LBS Autoencoder is a self-supervised method that fits articulated mesh models to point clouds without explicit correspondences, leveraging learned part-segmentations and LBS deformations for accurate registration.

Contribution

It introduces a self-supervised autoencoder that models pose-dependent deviations and uses structured Chamfer distance with learned segmentations for fitting meshes to point clouds.

Findings

Outperforms other unsupervised methods on body registration

Achieves comparable results to supervised approaches

Demonstrates effectiveness on real captured hand data

Abstract

We present LBS-AE; a self-supervised autoencoding algorithm for fitting articulated mesh models to point clouds. As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i.e. a template mesh equipped with a linear-blend skinning (LBS) deformation space parameterized by a skeleton hierarchy. As output, we learn an LBS-based autoencoder that produces registered meshes from the input point clouds. To bridge the gap between the artist-defined geometry and the captured point clouds, our autoencoder models pose-dependent deviations from the template geometry. During training, instead of using explicit correspondences, such as key points or pose supervision, our method leverages LBS deformations to bootstrap the learning process. To avoid poor local minima from erroneous point-to-point correspondences, we utilize a structured Chamfer distance based on part-segmentations, which are learned concurrently using self-supervision. We demonstrate qualitative results on real captured hands, and report quantitative evaluations on the FAUST benchmark for body registration. Our method achieves performance that is superior to other unsupervised approaches and comparable to methods using supervised examples.