DiffStyle360: Diffusion-Based 360° Head Stylization via Style Fusion Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guzelant, Furkan, Goktogan, Arda, Kaya, Tarık, Dundar, Aysegul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912734329700352
author Guzelant, Furkan
Goktogan, Arda
Kaya, Tarık
Dundar, Aysegul
author_facet Guzelant, Furkan
Goktogan, Arda
Kaya, Tarık
Dundar, Aysegul
contents 3D head stylization has emerged as a key technique for reimagining realistic human heads in various artistic forms, enabling expressive character design and creative visual experiences in digital media. Despite the progress in 3D-aware generation, existing 3D head stylization methods often rely on computationally expensive optimization or domain-specific fine-tuning to adapt to new styles. To address these limitations, we propose DiffStyle360, a diffusion-based framework capable of producing multi-view consistent, identity-preserving 3D head stylizations across diverse artistic domains given a single style reference image, without requiring per-style training. Building upon the 3D-aware DiffPortrait360 architecture, our approach introduces two key components: the Style Appearance Module, which disentangles style from content, and the Style Fusion Attention mechanism, which adaptively balances structure preservation and stylization fidelity in the latent space. Furthermore, we employ a 3D GAN-generated multi-view dataset for robust fine-tuning and introduce a temperaturebased key scaling strategy to control stylization intensity during inference. Extensive experiments on FFHQ and RenderMe360 demonstrate that DiffStyle360 achieves superior style quality, outperforming state-of-the-art GAN- and diffusion-based stylization methods across challenging style domains.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22411
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DiffStyle360: Diffusion-Based 360° Head Stylization via Style Fusion Attention
Guzelant, Furkan
Goktogan, Arda
Kaya, Tarık
Dundar, Aysegul
Computer Vision and Pattern Recognition
3D head stylization has emerged as a key technique for reimagining realistic human heads in various artistic forms, enabling expressive character design and creative visual experiences in digital media. Despite the progress in 3D-aware generation, existing 3D head stylization methods often rely on computationally expensive optimization or domain-specific fine-tuning to adapt to new styles. To address these limitations, we propose DiffStyle360, a diffusion-based framework capable of producing multi-view consistent, identity-preserving 3D head stylizations across diverse artistic domains given a single style reference image, without requiring per-style training. Building upon the 3D-aware DiffPortrait360 architecture, our approach introduces two key components: the Style Appearance Module, which disentangles style from content, and the Style Fusion Attention mechanism, which adaptively balances structure preservation and stylization fidelity in the latent space. Furthermore, we employ a 3D GAN-generated multi-view dataset for robust fine-tuning and introduce a temperaturebased key scaling strategy to control stylization intensity during inference. Extensive experiments on FFHQ and RenderMe360 demonstrate that DiffStyle360 achieves superior style quality, outperforming state-of-the-art GAN- and diffusion-based stylization methods across challenging style domains.
title DiffStyle360: Diffusion-Based 360° Head Stylization via Style Fusion Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.22411