# DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization

arXiv: https://arxiv.org/abs/2601.19717 · HTML: https://mlsanity.com/paper/2601.19717/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing](https://mlsanity.com/paper/2306.14435/) (2023)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [Style Aligned Image Generation via Shared Attention](https://mlsanity.com/paper/2312.02133/) (2023)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer](https://mlsanity.com/paper/2312.09008/) (2023)
- [StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting](https://mlsanity.com/paper/2403.07807/) (2024)
- [Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses](https://mlsanity.com/paper/1701.08893/) (2017)
- [UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene](https://mlsanity.com/paper/2208.07059/) (2022)
- [Attention Distillation: A Unified Approach to Visual Characteristics Transfer](https://mlsanity.com/paper/2502.20235/) (2025)
- [SGSST: Scaling Gaussian Splatting StyleTransfer](https://mlsanity.com/paper/2412.03371/) (2024)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [StyleSplat: 3D Object Style Transfer with Gaussian Splatting](https://mlsanity.com/paper/2407.09473/) (2024)
- [Texture Interpolation for Probing Visual Perception](https://mlsanity.com/paper/2006.03698/) (2020)
- [CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting](https://mlsanity.com/paper/2505.22854/) (2025)
- [Training-Free Sketch-Guided Diffusion with Latent Optimization](https://mlsanity.com/paper/2409.00313/) (2024)
- [StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians](https://mlsanity.com/paper/2504.15281/) (2025)
- [SplitFlux: Learning to Decouple Content and Style from a Single Image](https://mlsanity.com/paper/2511.15258/) (2025)
- [Prompt-Softbox-Prompt: A Free-Text Embedding Control for Image Editing](https://mlsanity.com/paper/2408.13623/) (2024)
- [ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylization](https://mlsanity.com/paper/2412.18783/) (2024)

## Abstract (arXiv)

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.