CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition

TL;DR

CloSET introduces a point-based method for modeling clothed human avatars that disentangles garment templates and pose-dependent wrinkles, enabling more accurate clothing deformation in unseen poses.

Contribution

The paper proposes a novel explicit template decomposition and point feature learning approach to improve clothing deformation modeling for animatable avatars.

Findings

Better clothing deformation results in unseen poses.

Effective disentanglement of garment templates and pose-dependent wrinkles.

Introduction of a high-quality human scan dataset with clothing.

Abstract

Creating animatable avatars from static scans requires the modeling of clothing deformations in different poses. Existing learning-based methods typically add pose-dependent deformations upon a minimally-clothed mesh template or a learned implicit template, which have limitations in capturing details or hinder end-to-end learning. In this paper, we revisit point-based solutions and propose to decompose explicit garment-related templates and then add pose-dependent wrinkles to them. In this way, the clothing deformations are disentangled such that the pose-dependent wrinkles can be better learned and applied to unseen poses. Additionally, to tackle the seam artifact issues in recent state-of-the-art point-based methods, we propose to learn point features on a body surface, which establishes a continuous and compact feature space to capture the fine-grained and pose-dependent clothing geometry. To facilitate the research in this field, we also introduce a high-quality scan dataset of humans in real-world clothing. Our approach is validated on two existing datasets and our newly introduced dataset, showing better clothing deformation results in unseen poses. The project page with code and dataset can be found at https://zhanghongwen.cn/closet.