AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization
2026-06-02 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionGraphics
AI summaryⓘ
The authors developed AvatarMix, a new way to swap outfits on 3D avatars without losing quality or causing parts to intersect awkwardly. Instead of mixing 2D images or modeling body and clothes separately, they combine high-quality 3D head and body models directly. They fix the tricky parts like the neck and hair join with a special tool called SeamFix, and can improve the whole body appearance with FullbodyFix if needed. Their method also reshapes the avatar's body to match different physiques accurately. Tests show their approach keeps outfit details and identity better than previous methods.
3D avataroutfit transferGaussian avatarsmesh retargeting3D consistencydiffusion modulebody reshapingidentity preservationartifact-free joinfull-body refinement
Authors
Zhaorong Wang, Yoshihiro Kanamori, Yuki Endo
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/