From 2D to 3D Geodesic-based Garment Matching

TL;DR

This paper introduces a novel method for retexturing garments from 2D images to 3D models using Gaussian mixture models and geodesic-based surface interpolation, improving realism in virtual clothing applications.

Contribution

It presents a new approach combining Gaussian mixture models and geodesic paths for more accurate 2D to 3D garment retexturing, enhancing realism over standard methods.

Findings

Lower mean square error compared to baseline methods

Higher mean opinion score indicating better perceived quality

Effective in matching garment boundaries and textures

Abstract

A new approach for 2D to 3D garment retexturing is proposed based on Gaussian mixture models and thin plate splines (TPS). An automatically segmented garment of an individual is matched to a new source garment and rendered, resulting in augmented images in which the target garment has been retextured by using the texture of the source garment. We divide the problem into garment boundary matching based on Gaussian mixture models and then interpolate inner points using surface topology extracted through geodesic paths, which leads to a more realistic result than standard approaches. We evaluated and compared our system quantitatively by mean square error (MSE) and qualitatively using the mean opinion score (MOS), showing the benefits of the proposed methodology on our gathered dataset.