ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction

2026-01-23

AI Summary

This work addresses the limitations of existing 3D garment reconstruction methods, which typically rely on unstructured representations that fail to preserve the topological and sewing structures of real garments, thereby hindering their use in physical simulation and robotic manipulation. To overcome this, the authors propose a novel approach that jointly reconstructs 3D garment geometry along with corresponding 2D patterns and seam lines from sparse multi-view RGB images—requiring as few as four views—and achieves, for the first time, end-to-end generation of structured, topology-consistent, and simulation-ready garment representations. By co-modeling in both 2D UV space and 3D space and leveraging a large-scale synthetic dataset (GCD-TS) for training, the method significantly outperforms prior work in topological accuracy, geometric alignment, and pattern-seam consistency, enabling direct application to high-fidelity physical simulation and robotic tasks.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

High-quality 3D garment reconstruction plays a crucial role in mitigating the sim-to-real gap in applications such as digital avatars, virtual try-on and robotic manipulation. However, existing garment reconstruction methods typically rely on unstructured representations, such as 3D Gaussian Splats, struggling to provide accurate reconstructions of garment topology and sewing structures. As a result, the reconstructed outputs are often unsuitable for high-fidelity physical simulation. We propose ReWeaver, a novel framework for topology-accurate 3D garment and sewing pattern reconstruction from sparse multi-view RGB images. Given as few as four input views, ReWeaver predicts seams and panels as well as their connectivities in both the 2D UV space and the 3D space. The predicted seams and panels align precisely with the multi-view images, yielding structured 2D--3D garment representations suitable for 3D perception, high-fidelity physical simulation, and robotic manipulation. To enable effective training, we construct a large-scale dataset GCD-TS, comprising multi-view RGB images, 3D garment geometries, textured human body meshes and annotated sewing patterns. The dataset contains over 100,000 synthetic samples covering a wide range of complex geometries and topologies. Extensive experiments show that ReWeaver consistently outperforms existing methods in terms of topology accuracy, geometry alignment and seam-panel consistency.

Problem

• garment reconstruction
• topology accuracy
• sewing structure
• physical simulation
• 3D garment

Innovation

• garment reconstruction
• topology accuracy
• sewing pattern
• physical simulation
• multi-view RGB