Skeleton-free Pose Transfer for Stylized 3D Characters

TL;DR

This paper introduces a novel method for automatically transferring poses between stylized 3D characters without relying on skeletal rigging, enabling pose transfer across diverse shapes and topologies.

Contribution

It proposes a unified articulation model and a pose transfer network that predicts skinning weights and deformation transformations for skeleton-free characters.

Findings

Effective pose transfer on diverse stylized characters

Generalizes well to unseen characters and objects

Outperforms existing methods in qualitative and quantitative evaluations

Abstract

We present the first method that automatically transfers poses between stylized 3D characters without skeletal rigging. In contrast to previous attempts to learn pose transformations on fixed or topology-equivalent skeleton templates, our method focuses on a novel scenario to handle skeleton-free characters with diverse shapes, topologies, and mesh connectivities. The key idea of our method is to represent the characters in a unified articulation model so that the pose can be transferred through the correspondent parts. To achieve this, we propose a novel pose transfer network that predicts the character skinning weights and deformation transformations jointly to articulate the target character to match the desired pose. Our method is trained in a semi-supervised manner absorbing all existing character data with paired/unpaired poses and stylized shapes. It generalizes well to unseen stylized characters and inanimate objects. We conduct extensive experiments and demonstrate the effectiveness of our method on this novel task.