DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization

• URL: http://arxiv.org/abs/2601.19717v1
• Date: Tue, 27 Jan 2026 15:41:11 GMT
• Title: DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization
• Authors: Yitong Yang, Xuexin Liu, Yinglin Wang, Jing Wang, Hao Dou, Changshuo Wang, Shuting He,
• Abstract summary: 3D style transfer enables the creation of visually expressive 3D content.<n>We propose DiffStyle3D, a novel diffusion-based paradigm for 3DGS style transfer.<n>We show that DiffStyle3D outperforms state-of-the-art methods, achieving higher stylization quality and visual realism.
• Score: 22.652699040654046
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D style transfer enables the creation of visually expressive 3D content, enriching the visual appearance of 3D scenes and objects. However, existing VGG- and CLIP-based methods struggle to model multi-view consistency within the model itself, while diffusion-based approaches can capture such consistency but rely on denoising directions, leading to unstable training. To address these limitations, we propose DiffStyle3D, a novel diffusion-based paradigm for 3DGS style transfer that directly optimizes in the latent space. Specifically, we introduce an Attention-Aware Loss that performs style transfer by aligning style features in the self-attention space, while preserving original content through content feature alignment. Inspired by the geometric invariance of 3D stylization, we propose a Geometry-Guided Multi-View Consistency method that integrates geometric information into self-attention to enable cross-view correspondence modeling. Based on geometric information, we additionally construct a geometry-aware mask to prevent redundant optimization in overlapping regions across views, which further improves multi-view consistency. Extensive experiments show that DiffStyle3D outperforms state-of-the-art methods, achieving higher stylization quality and visual realism.

Related papers

• StyleSculptor: Zero-Shot Style-Controllable 3D Asset Generation with Texture-Geometry Dual Guidance [50.207322685527394]
  StyleSculptor is a training-free approach for generating style-guided 3D assets from a content image and one or more style images.<n>It achieves style-guided 3D generation in a zero-shot manner, enabling fine-grained 3D style control.<n>In experiments, StyleSculptor outperforms existing baseline methods in producing high-fidelity 3D assets.
  arXiv  Detail & Related papers  (2025-09-16T17:55:20Z)
• SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer [57.723850794113055]
  We propose a novel 3D style transfer pipeline that integrates prior knowledge from pretrained 2D diffusion models.<n>Our pipeline consists of two key stages: First, we leverage diffusion priors to generate stylized renderings of key viewpoints.<n>The second is instance-level style transfer, which effectively leverages instance-level consistency across stylized key views and transfers it onto the 3D representation.
  arXiv  Detail & Related papers  (2025-09-04T16:40:44Z)
• Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control [47.14550252881733]
  We introduce techniques that enhance the quality of 3D stylization while maintaining view consistency and providing optional region-controlled style transfer.<n>Our method achieves stylization by re-training an initial 3D representation using stylized multi-view 2D images of the source views.<n>We propose Multi-Region Importance-Weighted Sliced Wasserstein Distance Loss, allowing styles to be applied to distinct image regions using segmentation masks from off-the-shelf models.
  arXiv  Detail & Related papers  (2025-09-04T15:01:01Z)
• Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation [9.212876623996475]
  Style3D is a novel approach for generating stylized 3D objects from a content image and a style image.<n>By establishing an interplay between structural and stylistic features across multiple views, our approach enables a holistic 3D stylization process.
  arXiv  Detail & Related papers  (2024-12-04T18:59:38Z)
• Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning [12.43848969320173]
  Stylized images from different viewpoints generated by our method achieve superior visual quality, with better structural integrity and less distortion. Our method effectively preserves the structural information and multi-view consistency in stylized images without any 3D information.
  arXiv  Detail & Related papers  (2024-11-15T12:02:07Z)
• 3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models [102.75875255071246]
  3D content creation via text-driven stylization has played a fundamental challenge to multimedia and graphics community. We propose a new 3DStyle-Diffusion model that triggers fine-grained stylization of 3D meshes with additional controllable appearance and geometric guidance from 2D Diffusion models.
  arXiv  Detail & Related papers  (2023-11-09T15:51:27Z)
• StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields [52.19291190355375]
  StyleRF (Style Radiance Fields) is an innovative 3D style transfer technique. It employs an explicit grid of high-level features to represent 3D scenes, with which high-fidelity geometry can be reliably restored via volume rendering. It transforms the grid features according to the reference style which directly leads to high-quality zero-shot style transfer.
  arXiv  Detail & Related papers  (2023-03-19T08:26:06Z)
• 3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations [81.45521258652734]
  We propose a method to create plausible geometric and texture style variations of 3D objects. Our method can create many novel stylized shapes, resulting in effortless 3D content creation and style-ware data augmentation.
  arXiv  Detail & Related papers  (2021-08-30T02:28:31Z)
• 3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer [66.48720190245616]
  We propose a learning-based approach for style transfer between 3D objects. The proposed method can synthesize new 3D shapes both in the form of point clouds and meshes. We extend our technique to implicitly learn the multimodal style distribution of the chosen domains.
  arXiv  Detail & Related papers  (2020-11-26T16:59:12Z)

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.