Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On

TL;DR

This paper introduces a novel generative model for 3D garments that inherently prevents collisions with the human body in virtual try-on, eliminating the need for postprocessing and improving realism across diverse shapes and motions.

Contribution

The paper presents a new data-driven, self-supervised approach for collision-free 3D garment deformation in virtual try-on, utilizing a canonical space and a diffused human body model.

Findings

Successfully addresses garment-body collisions in unseen shapes and motions

Outperforms existing methods in realism and detail preservation

First to integrate collision handling directly into generative modeling

Abstract

We propose a new generative model for 3D garment deformations that enables us to learn, for the first time, a data-driven method for virtual try-on that effectively addresses garment-body collisions. In contrast to existing methods that require an undesirable postprocessing step to fix garment-body interpenetrations at test time, our approach directly outputs 3D garment configurations that do not collide with the underlying body. Key to our success is a new canonical space for garments that removes pose-and-shape deformations already captured by a new diffused human body model, which extrapolates body surface properties such as skinning weights and blendshapes to any 3D point. We leverage this representation to train a generative model with a novel self-supervised collision term that learns to reliably solve garment-body interpenetrations. We extensively evaluate and compare our results with recently proposed data-driven methods, and show that our method is the first to successfully address garment-body contact in unseen body shapes and motions, without compromising realism and detail.