LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
This addresses the challenge of 3D registration for articulated objects like hands and bodies, offering a self-supervised solution that reduces the need for labeled data, though it is incremental as it builds on existing autoencoder and LBS techniques.
The paper tackles the problem of fitting articulated mesh models to point clouds without explicit correspondences or pose supervision, achieving performance superior to other unsupervised approaches and comparable to supervised methods on the FAUST benchmark.
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.