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

• URL: http://arxiv.org/abs/2606.03506v1
• Date: Tue, 02 Jun 2026 11:24:31 GMT
• Title: AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization
• Abstract summary: AvatarMix achieves state-of-the-art results in outfit fidelity and identity preservation, providing a new perspective for realistic 3D outfit personalization.<n>Our method achieves state-of-the-art results in outfit fidelity and identity preservation, providing a new perspective for realistic 3D outfit personalization.
• Score: 6.137762398583806
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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/

Related papers

• DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars [21.06532146412002]
  Existing 3D clothed avatar reconstruction methods achieve high visual fidelity but ignore geometric structure and physical plausibility.<n>We introduce DAMA, a 3D avatar reconstruction method that produces physically plausible clothed avatars through a dedicated representation and reconstruction method.<n>On the full 4D-DRESS dataset (82 scans), it achieves state-of-the-art performance in geometry reconstruction, garment separation, penetration rate, and depth.
  arXiv  Detail & Related papers  (2026-05-20T10:39:44Z)
• PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos [24.8968050268664]
  PFAvatar is a new method that reconstructs high-quality 3D avatars from Outfit of the Day (OOTD) photos.<n>Our method completes personalization in just 5 minutes, achieving a 48x speed-up compared to previous approaches.
  arXiv  Detail & Related papers  (2025-11-17T03:40:43Z)
• FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images [74.86864398919467]
  We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images.<n>We learn a universal prior from over a thousand clothed humans to achieve instant feedforward generation and zero-shot generalization.<n>Our method generates more authentic reconstruction and animation than state-of-the-arts, and can be directly generalized to inputs from casually taken phone photos.
  arXiv  Detail & Related papers  (2025-03-24T23:20:47Z)
• Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance [69.9745497000557]
  We introduce Arc2Avatar, the first SDS-based method utilizing a human face foundation model as guidance with just a single image as input.<n>Our avatars maintain a dense correspondence with a human face mesh template, allowing blendshape-based expression generation.
  arXiv  Detail & Related papers  (2025-01-09T17:04:33Z)
• LAGA: Layered 3D Avatar Generation and Customization via Gaussian Splatting [18.613001290226773]
  LAyered Gaussian Avatar (LAGA) is a framework enabling the creation of high-fidelity decomposable avatars with diverse garments.<n>By decoupling garments from avatar, our framework empowers users to conviniently edit avatars at the garment level.<n>Our approach surpasses existing methods in the generation of 3D clothed humans.
  arXiv  Detail & Related papers  (2024-05-21T10:24:06Z)
• LayGA: Layered Gaussian Avatars for Animatable Clothing Transfer [40.372917698238204]
  We present Layered Gaussian Avatars (LayGA), a new representation that formulates body and clothing as two separate layers. Our representation is built upon the Gaussian map-based avatar for its excellent representation power of garment details. In the single-layer reconstruction stage, we propose a series of geometric constraints to reconstruct smooth surfaces. In the multi-layer fitting stage, we train two separate models to represent body and clothing and utilize the reconstructed clothing geometries as 3D supervision.
  arXiv  Detail & Related papers  (2024-05-12T16:11:28Z)
• Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing [54.29207348918216]
  Cloth2Body needs to address new and emerging challenges raised by the partial observation of the input and the high diversity of the output. We propose an end-to-end framework that can accurately estimate 3D body mesh parameterized by pose and shape from a 2D clothing image. As shown by experimental results, the proposed framework achieves state-of-the-art performance and can effectively recover natural and diverse 3D body meshes from 2D images.
  arXiv  Detail & Related papers  (2023-09-28T06:18:38Z)
• AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion [34.609403685504944]
  We present AvatarFusion, a framework for zero-shot text-to-avatar generation. We use a latent diffusion model to provide pixel-level guidance for generating human-realistic avatars. We also introduce a novel optimization method, called Pixel-Semantics Difference-Sampling (PS-DS), which semantically separates the generation of body and clothes.
  arXiv  Detail & Related papers  (2023-07-13T02:19:56Z)
• DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models [55.71306021041785]
  We present DreamAvatar, a text-and-shape guided framework for generating high-quality 3D human avatars. We leverage the SMPL model to provide shape and pose guidance for the generation. We also jointly optimize the losses computed from the full body and from the zoomed-in 3D head to alleviate the common multi-face ''Janus'' problem.
  arXiv  Detail & Related papers  (2023-04-03T12:11:51Z)
• Capturing and Animation of Body and Clothing from Monocular Video [105.87228128022804]
  We present SCARF, a hybrid model combining a mesh-based body with a neural radiance field. integrating the mesh into the rendering enables us to optimize SCARF directly from monocular videos. We demonstrate that SCARFs clothing with higher visual quality than existing methods, that the clothing deforms with changing body pose and body shape, and that clothing can be successfully transferred between avatars of different subjects.
  arXiv  Detail & Related papers  (2022-10-04T19:34:05Z)
• ICON: Implicit Clothed humans Obtained from Normals [49.5397825300977]
  Implicit functions are well suited to the first task, as they can capture details like hair or clothes. ICON infers detailed clothed-human normals conditioned on the SMPL(-X) normals. ICON takes a step towards robust 3D clothed human reconstruction from in-the-wild images.
  arXiv  Detail & Related papers  (2021-12-16T18:59:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.