MD-Face: MoE-Enhanced Label-Free Disentangled Representation for Interactive Facial Attribute Editing

• URL: http://arxiv.org/abs/2604.20317v1
• Date: Wed, 22 Apr 2026 08:15:07 GMT
• Title: MD-Face: MoE-Enhanced Label-Free Disentangled Representation for Interactive Facial Attribute Editing
• Abstract summary: We propose MD-Face, a label-free disentangled representation learning framework based on Mixture of Experts (MoE)<n> MD-Face utilizes a MoE backbone with a gating mechanism that dynamically allocates experts, enabling the model to learn semantic vectors with greater independence.<n> Experiments with ProGAN and StyleGAN show that MD-Face outperforms unsupervised baselines and competes with supervised ones.
• Score: 5.354798606904701
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one face attribute unintentionally alters others. While supervised disentangled representation learning can address this, it relies heavily on labeled data, incurring high annotation costs. To address these challenges, we propose MD-Face, a label-free disentangled representation learning framework based on Mixture of Experts (MoE). MD-Face utilizes a MoE backbone with a gating mechanism that dynamically allocates experts, enabling the model to learn semantic vectors with greater independence. To further enhance attribute entanglement, we introduce a geometry-aware loss, which aligns each semantic vector with its corresponding Semantic Boundary Vector (SBV) through a Jacobian-based pushforward method. Experiments with ProGAN and StyleGAN show that MD-Face outperforms unsupervised baselines and competes with supervised ones. Compared to diffusion-based methods, it offers better image quality and lower inference latency, making it ideal for interactive editing.

Related papers

• Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation [63.90351637818903]
  Speech-preserving facial expression manipulation aims to enhance human expressiveness without altering mouth movements tied to the original speech.<n>Current Visual-Language Models (VLMs) can extract aligned visual and semantic features, making them a promising source of supervision.<n>We propose a Personalized Cross-Modal Emotional Correlation Learning algorithm that refines VLM-based supervision.
  arXiv  Detail & Related papers  (2026-04-28T06:02:23Z)
• AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing [78.6161238980415]
  AttDiff-GAN is a hybrid framework that combines GAN-based attribute manipulation with diffusion-based image generation.<n>We show that the proposed method achieves more accurate facial attribute editing and better preservation of non-target attributes than state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-23T05:05:46Z)
• LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulation [78.6161238980415]
  Conditional GANs have shown progress, but they are limited by accuracy issues and training instability.<n>We propose LatRef-Diff, a novel diffusion-based framework that addresses these limitations.<n>We show that LatRef-Diff achieves state-of-the-art performance in both qualitative and quantitative evaluations.
  arXiv  Detail & Related papers  (2026-04-23T04:47:40Z)
• ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment [70.19758313256503]
  We propose ICG, a framework that integrates MLLM-based prompting with personalized preference alignment to generate contextually relevant covers.<n>ICG extracts semantic features from item titles and reference images via meta tokens, refines them with user embeddings, and injects the resulting personalized context into the diffusion model.<n>Experiments demonstrate that ICG significantly improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy.
  arXiv  Detail & Related papers  (2026-04-08T06:36:54Z)
• U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning [15.353166784413306]
  We propose a novel framework designed to offer an effective and adaptable solution for unsupervised facial attribute editing.<n>The proposed method frames semantic vector learning as a subspace learning problem, where latent vectors are approximated within a lower-dimensional semantic subspace spanned by a semantic vector matrix.<n>We introduce non-negative constraints on the semantic vectors and incorporate attribute boundary vectors to reduce entanglement in the learned directions.
  arXiv  Detail & Related papers  (2026-03-14T16:09:56Z)
• Optimizing ID Consistency in Multimodal Large Models: Facial Restoration via Alignment, Entanglement, and Disentanglement [54.199726425201895]
  Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks.<n>Current facial ID preservation methods struggle to achieve consistent restoration of both facial identity and edited element IP.<n>We propose EditedID, an Alignment-Disentanglement-Entanglement framework for robust identity-specific facial restoration.
  arXiv  Detail & Related papers  (2026-02-21T08:24:42Z)
• ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion [40.50436862878818]
  We present a diffusion-based framework that faithfully reimagines any subject under any particular facial expression.<n>Our adapter generalizes beyond basic emotions to subtle micro-expressions and expressive transitions, overlooked by prior works.<n>In addition, a pluggable Reference Adapter enables expression editing in real images by transferring the appearance from a reference frame during synthesis.
  arXiv  Detail & Related papers  (2025-10-06T11:20:56Z)
• Attributes Shape the Embedding Space of Face Recognition Models [0.0]
  Face Recognition tasks have made significant progress with the advent of Deep Neural Networks.<n>We observe a multiscale geometric structure emerging in the embedding space.<n>We propose a geometric approach to describe the dependence or invariance of FR models to these attributes.
  arXiv  Detail & Related papers  (2025-07-15T14:44:39Z)
• OSDFace: One-Step Diffusion Model for Face Restoration [72.5045389847792]
  Diffusion models have demonstrated impressive performance in face restoration.<n>We propose OSDFace, a novel one-step diffusion model for face restoration.<n>Results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics.
  arXiv  Detail & Related papers  (2024-11-26T07:07:48Z)
• Dynamic Prototype Mask for Occluded Person Re-Identification [88.7782299372656]
  Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. We propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously.
  arXiv  Detail & Related papers  (2022-07-19T03:31:13Z)
• Learning Disentangled Representation for One-shot Progressive Face Swapping [92.09538942684539]
  We present a simple yet efficient method named FaceSwapper, for one-shot face swapping based on Generative Adversarial Networks.<n>Our method consists of a disentangled representation module and a semantic-guided fusion module.<n>Our method achieves state-of-the-art results on benchmark datasets with fewer training samples.
  arXiv  Detail & Related papers  (2022-03-24T11:19:04Z)
• InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs [73.27299786083424]
  We propose a framework called InterFaceGAN to interpret the disentangled face representation learned by state-of-the-art GAN models. We first find that GANs learn various semantics in some linear subspaces of the latent space. We then conduct a detailed study on the correlation between different semantics and manage to better disentangle them via subspace projection.
  arXiv  Detail & Related papers  (2020-05-18T18:01:22Z)

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.