Intersection-free Garment Retargeting

1Roblox, 2New York University
Siggraph 2025
Interpolate start reference image.

Our method retargets an artist-designed garment on a human avatar to a collection of virtual characters with various body shapes.

Abstract

Manual design of garments for avatars requires a large effort. Garment retargeting methods can save manual efforts by automatically deforming an existing garment design from one avatar to another. Previous methods are limited to human avatars with small variations in body shapes, while non-human avatars with unrealistic characteristics widely appear in games and animations. In this paper, the goal is to retarget artist-designed garments on a standard mannequin to a more general class of avatars. While there is a lack of training data of various avatars wearing garments, we propose a training-free method that performs optimizations on the mesh representation of the garments, with a combination of loss functions that preserve the geometrical features in the original design, guarantee intersection-free, and fit the garment adaptively to the avatars. Our method produces simulation-ready garment models that can be used later in avatar animations.

Algorithm pipeline

Results

Optimization process

Gallery

SMPL human models