H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks

• URL: http://arxiv.org/abs/2606.25578v1
• Date: Wed, 24 Jun 2026 08:52:06 GMT
• Title: H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks
• Abstract summary: H-Adapter improves pose robustness by training with a region-specific loss that disentangles hair and non-hair objectives.<n> Experiments on pose-agnostic and pose-different subsets demonstrate strong quantitative results.<n>We introduce a VLM-as-a-judge protocol and observe consistent gains in hairstyle faithfulness, non-hair preservation, and artifact quality.
• Score: 2.9567293946666173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hairstyle transfer has practical applications such as virtual try-on, yet remains challenging when the source and reference exhibit large head-pose discrepancies. We propose H-Adapter, which improves pose robustness by training with a region-specific loss that disentangles hair and non-hair objectives and thereby induces spatially disentangled cross-attention, from which a source-aligned hair edit mask is derived to guide diffusion-based inpainting. Experiments on pose-agnostic and pose-different subsets demonstrate strong quantitative results, including the best FID, $\mathrm{FID}_{\mathrm{CLIP}}$, and CLIP-I under pose differences, while maintaining competitive non-hair preservation and improving qualitative fidelity to fine-grained reference hairstyle details. Beyond source-conditioned transfer, H-Adapter supports practical extensions including text-to-image generation, auxiliary prompt-based hair color control, and compatibility with an identity-preserving IP-Adapter variant. We also introduce a VLM-as-a-judge protocol and observe consistent gains in hairstyle faithfulness, non-hair preservation, and artifact quality.

Related papers

• The Devil Is in the Leakage: A Disentangled Dual-Purification Framework for High-Fidelity Hairstyle Transfer [19.467144465203802]
  Hairstyle transfer aims to synthesize a portrait by transplanting the hairstyle from a reference image onto a source subject while preserving the source identity.<n>Recent foundation models show strong generative capability, but they struggle with the zero-shot disentanglement required for precise local editing.<n>We propose the Dual-Purification Framework (DPF), which introduces two complementary training-time regularizers.
  arXiv  Detail & Related papers  (2026-07-13T09:00:42Z)
• Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models [69.50286698375386]
  We propose a novel approach that better harnesses diffusion models for face-swapping. We introduce a mask shuffling technique during inpainting training, which allows us to create a so-called universal model for swapping. Ours is a relatively unified approach and so it is resilient to errors in other off-the-shelf models.
  arXiv  Detail & Related papers  (2024-09-11T13:43:53Z)
• What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer [35.80645300182437]
  Existing hairstyle transfer approaches rely on StyleGAN.<n>We propose a one-stage hairstyle transfer diffusion model, HairFusion, that applies to real-world scenarios.<n>Our method achieves state-of-the-art performance compared to the existing methods in preserving the integrity of both the transferred hairstyle and the surrounding features.
  arXiv  Detail & Related papers  (2024-08-29T11:30:21Z)
• Stable-Hair: Real-World Hair Transfer via Diffusion Model [26.880396643803998]
  Current hair transfer methods struggle to handle diverse and intricate hairstyles, limiting their applicability in real-world scenarios.<n>We propose a novel diffusion-based hair transfer framework, named textitStable-Hair, which robustly transfers a wide range of real-world hairstyles to user-provided faces for virtual hair try-on.
  arXiv  Detail & Related papers  (2024-07-19T07:14:23Z)
• DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation [84.0586749616249]
  This paper presents DiffFAE, a one-stage and highly-efficient diffusion-based framework tailored for high-fidelity Facial Appearance Editing. For high-fidelity query attributes transfer, we adopt Space-sensitive Physical Customization (SPC), which ensures the fidelity and generalization ability. In order to preserve source attributes, we introduce the Region-responsive Semantic Composition (RSC) This module is guided to learn decoupled source-regarding features, thereby better preserving the identity and alleviating artifacts from non-facial attributes such as hair, clothes, and background.
  arXiv  Detail & Related papers  (2024-03-26T12:53:10Z)
• HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending [94.39417893972262]
  HairCLIP is the first work that enables hair editing based on text descriptions or reference images. In this paper, we propose HairCLIPv2, aiming to support all the aforementioned interactions with one unified framework. The key idea is to convert all the hair editing tasks into hair transfer tasks, with editing conditions converted into different proxies accordingly.
  arXiv  Detail & Related papers  (2023-10-16T17:59:58Z)
• StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer [8.712040236361926]
  The paper seeks to transfer the hairstyle of a reference image to an input photo for virtual hair try-on. We propose a multi-view optimization framework that uses "two different views" of reference composites to semantically guide occluded or ambiguous regions. Our framework produces high-quality results and outperforms prior work in a user study that consists of significantly more challenging hair transfer scenarios.
  arXiv  Detail & Related papers  (2023-04-05T20:49:55Z)
• FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping [62.38898610210771]
  We present a new single-stage method for subject face swapping and identity transfer, named FaceDancer. We have two major contributions: Adaptive Feature Fusion Attention (AFFA) and Interpreted Feature Similarity Regularization (IFSR)
  arXiv  Detail & Related papers  (2022-10-19T11:31:38Z)
• Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment [29.782276472922398]
  We propose a pose-invariant hairstyle transfer model equipped with latent optimization and a newly presented local-style-matching loss. Our model has strengths in transferring a hairstyle under larger pose differences and preserving local hairstyle textures.
  arXiv  Detail & Related papers  (2022-08-16T14:23:54Z)
• HairCLIP: Design Your Hair by Text and Reference Image [100.85116679883724]
  This paper proposes a new hair editing interaction mode, which enables manipulating hair attributes individually or jointly. We encode the image and text conditions in a shared embedding space and propose a unified hair editing framework. With the carefully designed network structures and loss functions, our framework can perform high-quality hair editing.
  arXiv  Detail & Related papers  (2021-12-09T18:59:58Z)
• MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing [122.82964863607938]
  MichiGAN is a novel conditional image generation method for interactive portrait hair manipulation. We provide user control over every major hair visual factor, including shape, structure, appearance, and background. We also build an interactive portrait hair editing system that enables straightforward manipulation of hair by projecting intuitive and high-level user inputs.
  arXiv  Detail & Related papers  (2020-10-30T17:59:10Z)

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.