NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments

TL;DR

NeuralTailor is a novel neural network architecture that accurately reconstructs 2D sewing patterns from 3D garment point clouds, enabling better generalization across diverse garment designs in virtual applications.

Contribution

The paper introduces NeuralTailor, a set regression model with point-level attention that reconstructs sewing patterns from 3D garments and generalizes to unseen garment types.

Findings

Successfully reconstructs sewing patterns from 3D point clouds.

Generalizes to garment types with unseen pattern topologies.

Outperforms existing methods in pattern reconstruction accuracy.

Abstract

The fields of SocialVR, performance capture, and virtual try-on are often faced with a need to faithfully reproduce real garments in the virtual world. One critical task is the disentanglement of the intrinsic garment shape from deformations due to fabric properties, physical forces, and contact with the body. We propose to use a garment sewing pattern, a realistic and compact garment descriptor, to facilitate the intrinsic garment shape estimation. Another major challenge is a high diversity of shapes and designs in the domain. The most common approach for Deep Learning on 3D garments is to build specialized models for individual garments or garment types. We argue that building a unified model for various garment designs has the benefit of generalization to novel garment types, hence covering a larger design domain than individual models would. We introduce NeuralTailor, a novel architecture based on point-level attention for set regression with variable cardinality, and apply it to the task of reconstructing 2D garment sewing patterns from the 3D point could garment models. Our experiments show that NeuralTailor successfully reconstructs sewing patterns and generalizes to garment types with pattern topologies unseen during training.