Mixture of Style Experts for Diverse Image Stylization

• URL: http://arxiv.org/abs/2603.16649v2
• Date: Thu, 19 Mar 2026 08:05:32 GMT
• Title: Mixture of Style Experts for Diverse Image Stylization
• Abstract summary: StyleExpert is a semantic-aware framework based on the Mixture of Experts (MoE)<n>Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets.<n>Our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics.
• Score: 73.7600741657193
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the Mixture of Experts (MoE). Our framework employs a unified style encoder, trained on our large-scale dataset of content-style-stylized triplets, to embed diverse styles into a consistent latent space. This embedding is then used to condition a similarity-aware gating mechanism, which dynamically routes styles to specialized experts within the MoE architecture. Leveraging this MoE architecture, our method adeptly handles diverse styles spanning multiple semantic levels, from shallow textures to deep semantics. Extensive experiments show that StyleExpert outperforms existing approaches in preserving semantics and material details, while generalizing to unseen styles. Our code and collected images are available at the project page: https://hh-lg.github.io/StyleExpert-Page/.

Related papers

• Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning [52.33837657928263]
  Style transfer, given content and style references, remains challenging for Diffusion Transformers.<n>We propose Style-CCL, a Multi-Stage Curriculum Continual Learning framework that trains SC-DiT from semantic (easy) to texture (hard) styles.<n>Our framework achieves state-of-the-art performance in three core metrics: style similarity, content consistency, and aesthetic quality.
  arXiv  Detail & Related papers  (2026-06-04T13:02:04Z)
• StyleDecoupler: Generalizable Artistic Style Disentanglement [24.48314583152099]
  StyleDecoupler is an information-theoretic framework for representing artistic style.<n>We also introduce WeART, a large-scale benchmark of 280K artworks across 152 styles and 1,556 artists.
  arXiv  Detail & Related papers  (2026-01-25T05:09:30Z)
• Pluggable Style Representation Learning for Multi-Style Transfer [41.09041735653436]
  We develop a style transfer framework by decoupling the style modeling and transferring.<n>For style modeling, we propose a style representation learning scheme to encode the style information into a compact representation.<n>For style transferring, we develop a style-aware multi-style transfer network (SaMST) to adapt to diverse styles using pluggable style representations.
  arXiv  Detail & Related papers  (2025-03-26T09:44:40Z)
• ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences [33.06053818091165]
  ReStyle3D is a framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views.<n>It combines explicit semantic correspondences with multi-view consistency to achieve precise and coherent stylization.<n>Our code, pretrained models, and dataset will be publicly released to support new applications in interior design, virtual staging, and 3D-consistent stylization.
  arXiv  Detail & Related papers  (2025-02-14T18:54:21Z)
• StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples [48.44036251656947]
  Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content.<n>We introduce StyleDistance, a novel approach to training stronger content-independent style embeddings.
  arXiv  Detail & Related papers  (2024-10-16T17:25:25Z)
• StyleBrush: Style Extraction and Transfer from a Single Image [19.652575295703485]
  Stylization for visual content aims to add specific style patterns at the pixel level while preserving the original structural features. We propose StyleBrush, a method that accurately captures styles from a reference image and brushes'' the extracted style onto other input visual content.
  arXiv  Detail & Related papers  (2024-08-18T14:27:20Z)
• StyleShot: A Snapshot on Any Style [20.41380860802149]
  We show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning.<n>We achieve this through constructing a style-aware encoder and a well-organized style dataset called StyleGallery.<n>We highlight that, our approach, named StyleShot, is simple yet effective in mimicking various desired styles, without test-time tuning.
  arXiv  Detail & Related papers  (2024-07-01T16:05:18Z)
• ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model [73.95608242322949]
  Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images. We present ArtWeaver, a novel framework that leverages pretrained Stable Diffusion to address challenges such as misinterpreted styles and inconsistent semantics.
  arXiv  Detail & Related papers  (2024-05-24T07:19:40Z)
• Styleverse: Towards Identity Stylization across Heterogeneous Domains [70.13327076710269]
  We propose a new challenging task namely IDentity Stylization (IDS) across heterogeneous domains. We use an effective heterogeneous-network-based framework $Styleverse$ that uses a single domain-aware generator. $Styleverse achieves higher-fidelity identity stylization compared with other state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-03-02T04:23:01Z)
• StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval [119.03470556503942]
  Crossmodal matching problem is typically solved by learning a joint embedding space where semantic content shared between photo and sketch modalities are preserved. An effective model needs to explicitly account for this style diversity, crucially, to unseen user styles. Our model can not only disentangle the cross-modal shared semantic content, but can adapt the disentanglement to any unseen user style as well, making the model truly agnostic.
  arXiv  Detail & Related papers  (2021-03-29T15:44:19Z)

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.