LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending

2026-05-08

AI Summary

This work addresses the challenging problem of garment refitting between source and target avatars with significantly different body shapes and no standardized rest poses. To this end, the authors propose a novel approach based on a hybrid representation leveraging local bone mappings. The method expresses garment geometry as a linear blend in local bone coordinate systems, combined with local residual optimization and collision handling to effectively decouple global non-local dependencies and construct a smooth optimization landscape. The proposed technique achieves stable refitting across large deformations and topological discrepancies for both high-resolution single-layer and multi-layer garments, demonstrating substantial improvements over existing methods in terms of detail preservation, fitting quality, convergence stability, and generalization capability.

Abstract

Garment refitting, the task of adapting a garment from a source to a target avatar, must preserve the original design features and fine-scale wrinkles, a challenge exacerbated by significant shape variations and varying poses without registration to a shared canonical pose. Existing methods struggle to balance robustness, efficiency, and fidelity of detail: physics-based simulation is costly, data-driven approaches lack generalizability, and geometry optimization in the full vertex space is often ill-conditioned and prone to local minima with unsatisfactory quality. We identify that a fundamental limitation lies in the representation: deforming garments directly in global coordinates couples vertices non-locally, creating a complex and poorly-structured optimization landscape. Therefore, we introduce LoBoFit, a robust refitting method built upon a novel Local Bone Mapping Blending (LoBoMap Blending) representation. Instead of manipulating global vertex positions, LoBoMap Blending expresses garment geometry as a linear blend of its mappings into local bone coordinate frames. This representation is highly expressive and flexible: local bone mappings yield a pose-robust initialization and a well-conditioned parameterization, while blending weights smooth the optimization landscape and broaden the space of plausible solutions for stable convergence with fine-scale detail preservation. The subsequent refinement efficiently resolves collisions and preserves details by optimizing localized residuals, effectively decomposing the complex global deformation into manageable subproblems. Our experiments demonstrate that LoBoFit reliably refits high-resolution, single- and multi-layer garments across avatars with large shape and topological differences, while faithfully preserving intricate wrinkles and the intended fit style, outperforming state-of-the-art methods in robustness and output quality.

Problem

• garment refitting
• shape variation
• pose variation
• detail preservation
• avatar

Innovation

• Local Bone Mapping Blending
• Garment Refitting
• Pose-Robust Representation
• Detail Preservation
• Optimization Decomposition