单图生成多视角3D风格化场景，无需优化与预设姿态。
Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting
- 采用双路径Transformer架构，分别处理几何与风格
- 零样本跨类别、跨场景实现视图一致的高质量风格迁移
- 适合快速3D内容创作与风格化应用开发
我们提出Stylos，一种基于单次前向传播的3D高斯框架，可对无姿态约束的内容（从单张图像到多视角集合）进行3D风格迁移，参考一张独立的风格图像。该方法无需逐场景优化或预计算姿态，即可实现几何感知且视图一致的风格化，泛化能力覆盖未见类别、场景和风格。核心采用带双路径的Transformer：几何预测保留自注意力以保持几何保真度，风格通过全局交叉注意力注入以确保跨视角视觉一致性。引入基于体素的3D风格损失，将聚合场景特征对齐至风格统计量，进一步强化视图一致性并保留几何结构。在多个数据集上的实验表明，Stylos实现了高质量的零样本风格迁移，验证了全局风格-内容耦合、所提3D风格损失的有效性，以及从单视角到大规模多视角设置的可扩展性。代码已开源于https://github.com/HanzhouLiu/Stylos。
原文摘要 · Abstract (English)
We present Stylos, a single-forward 3D Gaussian framework for 3D style transfer that operates on unposed content, from a single image to a multi-view collection, conditioned on a separate reference style image. Stylos synthesizes a stylized 3D Gaussian scene without per-scene optimization or precomputed poses, achieving geometry-aware, view-consistent stylization that generalizes to unseen categories, scenes, and styles. At its core, Stylos adopts a Transformer backbone with two pathways: geometry predictions retain self-attention to preserve geometric fidelity, while style is injected via global cross-attention to enforce visual consistency across views. With the addition of a voxel-based 3D style loss that aligns aggregated scene features to style statistics, Stylos enforces view-consistent stylization while preserving geometry. Experiments across multiple datasets demonstrate that Stylos delivers high-quality zero-shot stylization, highlighting the effectiveness of global style-content coupling, the proposed 3D style loss, and the scalability of our framework from single view to large-scale multi-view settings. Our codes are available at https://github.com/HanzhouLiu/Stylos.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。