Style3D：用于3D物体生成的注意力引导多视图风格迁移
Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation
AI总结：
本文提出 Style3D，通过 MultiFusion Attention 对齐多视图内容与风格特征，并结合大型3D重建模型，实现无需特定训练、高效且高质量的即时3D物体风格化。
摘要：
我们提出了 Style3D，这是一种根据内容图像和风格图像生成风格化3D物体的新颖方法。不同于以往大多数需要针对具体案例或特定风格进行训练的方法，Style3D 支持即时的3D物体风格化。我们的核心洞察是，3D物体风格化可以分解为两个相互关联的过程：多视图双特征对齐和稀疏视图空间重建。我们引入了 MultiFusion Attention，这是一种注意力引导技术，用于从内容-风格图像对实现多视图风格化。具体而言，来自内容图像的 query 特征保持多个视图之间的几何一致性，而来自风格图像的 key 和 value 特征则用于引导风格迁移。这种双特征对齐确保在多视图图像之间维持空间连贯性和风格保真度。最后，我们引入一个大型3D重建模型来生成连贯的风格化3D物体。通过在多个视图之间建立结构特征与风格特征的相互作用，我们的方法实现了整体化的3D风格化过程。大量实验表明，Style3D 为生成风格一致的3D资产提供了更灵活、更可扩展的解决方案，并在计算效率和视觉质量方面均超越现有方法。
英文摘要：
We present Style3D, a novel approach for generating stylized 3D objects from a content image and a style image. Unlike most previous methods that require case- or style-specific training, Style3D supports instant 3D object stylization. Our key insight is that 3D object stylization can be decomposed into two interconnected processes: multi-view dual-feature alignment and sparse-view spatial reconstruction. We introduce MultiFusion Attention, an attention-guided technique to achieve multi-view stylization from the content-style pair. Specifically, the query features from the content image preserve geometric consistency across multiple views, while the key and value features from the style image are used to guide the stylistic transfer. This dual-feature alignment ensures that spatial coherence and stylistic fidelity are maintained across multi-view images. Finally, a large 3D reconstruction model is introduced to generate coherent stylized 3D objects. By establishing an interplay between structural and stylistic features across multiple views, our approach enables a holistic 3D stylization process. Extensive experiments demonstrate that Style3D offers a more flexible and scalable solution for generating style-consistent 3D assets, surpassing existing methods in both computational efficiency and visual quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
