Detail-aware Deep Clothing Animations Infused with Multi-source Attributes

TL;DR

This paper introduces a unified learning-based method for detailed clothing deformation that adapts to various body shapes and animations, improving realism and efficiency over existing approaches.

Contribution

A novel framework that predicts rich garment deformations using multi-source attributes, with strategies for attribute encoding and output reconstruction to enhance detail and generalization.

Findings

Outperforms existing methods in detail quality and generalization

Efficiently produces high-fidelity deformations for diverse garments and poses

Enhances deformation realism by considering garment-body fit and attribute influence

Abstract

This paper presents a novel learning-based clothing deformation method to generate rich and reasonable detailed deformations for garments worn by bodies of various shapes in various animations. In contrast to existing learning-based methods, which require numerous trained models for different garment topologies or poses and are unable to easily realize rich details, we use a unified framework to produce high fidelity deformations efficiently and easily. To address the challenging issue of predicting deformations influenced by multi-source attributes, we propose three strategies from novel perspectives. Specifically, we first found that the fit between the garment and the body has an important impact on the degree of folds. We then designed an attribute parser to generate detail-aware encodings and infused them into the graph neural network, therefore enhancing the discrimination of details under diverse attributes. Furthermore, to achieve better convergence and avoid overly smooth deformations, we proposed output reconstruction to mitigate the complexity of the learning task. Experiment results show that our proposed deformation method achieves better performance over existing methods in terms of generalization ability and quality of details.