ClothCombo: Modeling Inter-Cloth Interaction for Draping Multi-Layered Clothes

TL;DR

ClothCombo introduces a GNN-based pipeline for realistic multi-layered clothing draping on 3D human models, effectively modeling inter-cloth interactions and resolving interpenetrations across diverse poses.

Contribution

The paper proposes a novel GNN-based approach that models inter-cloth interactions for multi-layered clothing draping, overcoming previous limitations in topology dependence.

Findings

Strong performance in complex multi-layered scenarios

Effective modeling of inter-cloth interactions

Applicable to diverse poses and clothing combinations

Abstract

We present ClothCombo, a pipeline to drape arbitrary combinations of clothes on 3D human models with varying body shapes and poses. While existing learning-based approaches for draping clothes have shown promising results, multi-layered clothing remains challenging as it is non-trivial to model inter-cloth interaction. To this end, our method utilizes a GNN-based network to efficiently model the interaction between clothes in different layers, thus enabling multi-layered clothing. Specifically, we first create feature embedding for each cloth using a topology-agnostic network. Then, the draping network deforms all clothes to fit the target body shape and pose without considering inter-cloth interaction. Lastly, the untangling network predicts the per-vertex displacements in a way that resolves interpenetration between clothes. In experiments, the proposed model demonstrates strong performance in complex multi-layered scenarios. Being agnostic to cloth topology, our method can be readily used for layered virtual try-on of real clothes in diverse poses and combinations of clothes.