StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yuanlin, Song, Quanjian, Gao, Zhexian, Wang, Ge, Li, Shanshan, Zhang, Xiaoyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918111990513664
author Yang, Yuanlin
Song, Quanjian
Gao, Zhexian
Wang, Ge
Li, Shanshan
Zhang, Xiaoyan
author_facet Yang, Yuanlin
Song, Quanjian
Gao, Zhexian
Wang, Ge
Li, Shanshan
Zhang, Xiaoyan
contents Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the semantic gap between the non-spatial nature of textual descriptions and the spatially-aware attributes of visual style, often leading to the loss of semantic structure and fine-grained details during stylization. In this paper, we propose StyDeco, an unsupervised framework that resolves this limitation by learning text representations specifically tailored for the style transfer task. Our framework first employs Prior-Guided Data Distillation (PGD), a strategy designed to distill stylistic knowledge without human supervision. It leverages a powerful frozen generative model to automatically synthesize pseudo-paired data. Subsequently, we introduce Contrastive Semantic Decoupling (CSD), a task-specific objective that adapts a text encoder using domain-specific weights. CSD performs a two-class clustering in the semantic space, encouraging source and target representations to form distinct clusters. Extensive experiments on three classic benchmarks demonstrate that our framework outperforms several existing approaches in both stylistic fidelity and structural preservation, highlighting its effectiveness in style transfer with semantic preservation. In addition, our framework supports a unique de-stylization process, further demonstrating its extensibility. Our code is vailable at https://github.com/QuanjianSong/StyDeco.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01215
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling
Yang, Yuanlin
Song, Quanjian
Gao, Zhexian
Wang, Ge
Li, Shanshan
Zhang, Xiaoyan
Computer Vision and Pattern Recognition
Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the semantic gap between the non-spatial nature of textual descriptions and the spatially-aware attributes of visual style, often leading to the loss of semantic structure and fine-grained details during stylization. In this paper, we propose StyDeco, an unsupervised framework that resolves this limitation by learning text representations specifically tailored for the style transfer task. Our framework first employs Prior-Guided Data Distillation (PGD), a strategy designed to distill stylistic knowledge without human supervision. It leverages a powerful frozen generative model to automatically synthesize pseudo-paired data. Subsequently, we introduce Contrastive Semantic Decoupling (CSD), a task-specific objective that adapts a text encoder using domain-specific weights. CSD performs a two-class clustering in the semantic space, encouraging source and target representations to form distinct clusters. Extensive experiments on three classic benchmarks demonstrate that our framework outperforms several existing approaches in both stylistic fidelity and structural preservation, highlighting its effectiveness in style transfer with semantic preservation. In addition, our framework supports a unique de-stylization process, further demonstrating its extensibility. Our code is vailable at https://github.com/QuanjianSong/StyDeco.
title StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.01215