SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows
This work addresses the need for more adaptable and efficient animation tools for artists and creators in digital media, though it appears incremental as it builds on existing IK and SMPL frameworks.
The paper tackles the problem of rigid inverse kinematics (IK) systems that require manual adaptation for different human morphologies, by developing SMPL-IK, a learned IK solver that extends a state-of-the-art method to the SMPL model, enabling flexible pose authoring and integration with 2D image-based pose estimation for faster 3D scene creation.
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.