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

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.

Updated to the version accepted to SIGGRAPH 2022 (Journal Track)

References in corpus (5)

• A Neural Representation of Sketch Drawings
• DeepCloth: Neural Garment Representation for Shape and Style Editing
• StructureNet: Hierarchical Graph Networks for 3D Shape Generation
• DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning
• The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts

Cited by in corpus (3)

• Towards Garment Sewing Pattern Reconstruction from a Single Image
• GarmentCode: Programming Parametric Sewing Patterns
• EASE: Parametric garment design with explicit and local ease control