Point-Based Modeling of Human Clothing

TL;DR

This paper introduces a novel point cloud-based deep learning approach for modeling human clothing, enabling the prediction, retargeting, and appearance rendering of outfits across various poses and body shapes.

Contribution

It presents a unified point cloud model capable of handling diverse clothing types and topologies, with applications in inferring geometry from images and re-rendering outfits from videos.

Findings

The model accurately predicts clothing geometry across different outfits and poses.

It can infer outfit geometry from a single image.

The approach effectively captures and re-renders outfit appearance from videos.

Abstract

We propose a new approach to human clothing modeling based on point clouds. Within this approach, we learn a deep model that can predict point clouds of various outfits, for various human poses, and for various human body shapes. Notably, outfits of various types and topologies can be handled by the same model. Using the learned model, we can infer the geometry of new outfits from as little as a single image, and perform outfit retargeting to new bodies in new poses. We complement our geometric model with appearance modeling that uses the point cloud geometry as a geometric scaffolding and employs neural point-based graphics to capture outfit appearance from videos and to re-render the captured outfits. We validate both geometric modeling and appearance modeling aspects of the proposed approach against recently proposed methods and establish the viability of point-based clothing modeling.