SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows

TL;DR

SMPL-IK is a flexible, learned inverse kinematics system that adapts to various human morphologies, enabling AI-assisted animation workflows and supporting custom characters through shape inversion.

Contribution

The paper introduces SMPL-IK, a novel morphology-aware IK solver that extends existing models to work with diverse human shapes and includes a shape inversion mechanism for custom characters.

Findings

Enables pose authoring with adjustable gender and body shape.

Accelerates scene creation from 2D images using pose estimation.

Provides quantitative benchmarks on H36M and AMASS datasets.

Abstract

Inverse Kinematics (IK) systems are often rigid with respect to their input character, thus requiring user intervention to be adapted to new skeletons. In this paper we aim at creating a flexible, learned IK solver applicable to a wide variety of human morphologies. We extend a state-of-the-art machine learning IK solver to operate on the well known Skinned Multi-Person Linear model (SMPL). We call our model SMPL-IK, and show that when integrated into real-time 3D software, this extended system opens up opportunities for defining novel AI-assisted animation workflows. For example, pose authoring can be made more flexible with SMPL-IK by allowing users to modify gender and body shape while posing a character. Additionally, when chained with existing pose estimation algorithms, SMPL-IK accelerates posing by allowing users to bootstrap 3D scenes from 2D images while allowing for further editing. Finally, we propose a novel SMPL Shape Inversion mechanism (SMPL-SI) to map arbitrary humanoid characters to the SMPL space, allowing artists to leverage SMPL-IK on custom characters. In addition to qualitative demos showing proposed tools, we present quantitative SMPL-IK baselines on the H36M and AMASS datasets.