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

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.

arXiv commentIn the Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)

References in corpus (12)

• Geometric deep learning: going beyond Euclidean data
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Improved Training of Wasserstein GANs
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Embodied Hands: Modeling and Capturing Hands and Bodies Together
• Learning from Synthetic Humans
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Learning Representations and Generative Models for 3D Point Clouds
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Unite the People: Closing the Loop Between 3D and 2D Human Representations
• SurfNet: Generating 3D shape surfaces using deep residual networks
• Unsupervised Training for 3D Morphable Model Regression