CVAIApr 14, 2021

LEAP: Learning Articulated Occupancy of People

arXiv:2104.06849v1145 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of creating accurate 3D human models for applications like animation and VR, representing an incremental advance over prior rigid object methods.

The paper tackles the problem of modeling human body shape and pose deformations using neural implicit representations, introducing LEAP which improves generalization to unseen subjects and poses, outperforming existing methods in all settings.

Substantial progress has been made on modeling rigid 3D objects using deep implicit representations. Yet, extending these methods to learn neural models of human shape is still in its infancy. Human bodies are complex and the key challenge is to learn a representation that generalizes such that it can express body shape deformations for unseen subjects in unseen, highly-articulated, poses. To address this challenge, we introduce LEAP (LEarning Articulated occupancy of People), a novel neural occupancy representation of the human body. Given a set of bone transformations (i.e. joint locations and rotations) and a query point in space, LEAP first maps the query point to a canonical space via learned linear blend skinning (LBS) functions and then efficiently queries the occupancy value via an occupancy network that models accurate identity- and pose-dependent deformations in the canonical space. Experiments show that our canonicalized occupancy estimation with the learned LBS functions greatly improves the generalization capability of the learned occupancy representation across various human shapes and poses, outperforming existing solutions in all settings.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes