PhyDeformer: High-Quality Non-Rigid Garment Registration with Physics-Awareness

2025-01-14

AI Summary

Existing 3D garment models suffer from significant deficiencies in geometric alignment and fine-detail fidelity. This paper proposes a two-stage non-rigid clothing mesh registration method: Stage I performs proportion-adaptive pattern scaling based on garment grading to achieve coarse-grained global alignment; Stage II introduces a physics-aware Jacobian-based deformation framework, jointly optimizing local deformations under multi-scale geometric constraints to ensure both physical plausibility and accurate wrinkle reproduction. To our knowledge, this is the first work to deeply integrate Jacobian-driven deformation with garment grading modeling, thereby overcoming the longstanding trade-off between global adaptability and local fidelity inherent in prior approaches. Extensive evaluations on both synthetic and real-world datasets demonstrate that our method significantly outperforms state-of-the-art methods—achieving a 28.6% reduction in Chamfer distance—and yields more natural deformations and more accurate wrinkle structures.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: Manipulation
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Large-scale security measurements

Abstract

We present PhyDeformer, a new deformation method for high-quality garment mesh registration. It operates in two phases: In the first phase, a garment grading is performed to achieve a coarse 3D alignment between the mesh template and the target mesh, accounting for proportional scaling and fit (e.g. length, size). Then, the graded mesh is refined to align with the fine-grained details of the 3D target through an optimization coupled with the Jacobian-based deformation framework. Both quantitative and qualitative evaluations on synthetic and real garments highlight the effectiveness of our method.

Problem

• 3D Garment Modeling
• Shape Matching
• Detail Replication

Innovation

• PhyDeformer
• Physical Knowledge
• 3D Garment Modeling