AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization

2026-06-02

AI Summary

Existing methods for outfit transfer on 3D avatars struggle to simultaneously preserve identity consistency, maintain fine garment details, and prevent interpenetration between clothing and body. This work proposes a compositional outfit transfer paradigm that achieves dressing by fusing the head and body of two high-fidelity Gaussian avatars. A two-stage optimization strategy is introduced: first, mesh retargeting and a cross-avatar composition mechanism retain user identity while avoiding interpenetration; second, SeamFix and FullbodyFix modules perform localized seam refinement and global appearance optimization, respectively. The approach further leverages mesh-based Gaussian representations and 3D-consistent rendering to enhance visual fidelity. Experiments demonstrate that the proposed method significantly outperforms existing techniques in both identity preservation and garment fidelity, enabling high-quality outfit transfer across diverse body shapes.

Abstract

Existing 3D avatar outfit transfer methods face distinct challenges: approaches that lift 2D edits to 3D often suffer from outfit or identity quality degradation, while those that separately model body and clothing layers are prone to intersection artifacts. We introduce AvatarMix, a compositional paradigm that bypasses these issues by directly composing the head and body from two high-fidelity Gaussian avatars. While this paradigm inherently preserves outfit quality and avoids intersections, it introduces challenges in creating a seamless join and maintaining appearance fidelity after body reshaping. To this end, we propose a two-tier refinement strategy: SeamFix, a localized diffusion module that refines hair and neck to ensure an artifact-free join, and an optional full-body refinement, FullbodyFix, that restores garment appearance when retargeting degrades the clothed body. Both operate on renders from an already 3D-consistent Gaussian avatar, which limits multi-view artifacts compared to 2D-to-3D lifting. To preserve the user's body identity, our mesh-based Gaussian representation enables the adaptation of a robust mesh retargeting technique, precisely reshaping the clothed body to the user's physique and robustly handling diverse body shapes. Extensive experiments demonstrate that our method achieves state-of-the-art results in outfit fidelity and identity preservation, providing a new perspective for realistic 3D outfit personalization. Project page: https://larsph.github.io/avatarmix/

Problem

• avatar composition
• outfit personalization
• identity preservation
• 3D avatar
• garment transfer

Innovation

• Gaussian Avatars
• Identity Preservation
• Outfit Personalization
• Seamless Composition
• Mesh Retargeting