DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images

TL;DR

DressWild introduces a fast, pose-agnostic method for generating realistic sewing patterns and 3D garments from single in-the-wild images, enabling scalable garment modeling and virtual try-on applications.

Contribution

The paper presents a novel feed-forward pipeline that reconstructs physics-consistent sewing patterns and 3D garments from single images, overcoming pose and viewpoint limitations of prior methods.

Findings

Robustly recovers diverse sewing patterns from in-the-wild images

Does not require multi-view inputs or iterative optimization

Enables efficient garment simulation and virtual try-on

Abstract

Recent advances in garment pattern generation have shown promising progress. However, existing feed-forward methods struggle with diverse poses and viewpoints, while optimization-based approaches are computationally expensive and difficult to scale. This paper focuses on sewing pattern generation for garment modeling and fabrication applications that demand editable, separable, and simulation-ready garments. We propose DressWild, a novel feed-forward pipeline that reconstructs physics-consistent 2D sewing patterns and the corresponding 3D garments from a single in-the-wild image. Given an input image, our method leverages vision-language models (VLMs) to normalize pose variations at the image level, then extract pose-aware, 3D-informed garment features. These features are fused through a transformer-based encoder and subsequently used to predict sewing pattern parameters, which can be directly applied to physical simulation, texture synthesis, and multi-layer virtual try-on. Extensive experiments demonstrate that our approach robustly recovers diverse sewing patterns and the corresponding 3D garments from in-the-wild images without requiring multi-view inputs or iterative optimization, offering an efficient and scalable solution for realistic garment simulation and animation.