Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation

TL;DR

Style3D introduces an attention-guided multi-view style transfer method that enables instant, coherent stylization of 3D objects from content and style images, improving efficiency and visual quality.

Contribution

It proposes a novel multi-view dual-feature alignment technique with MultiFusion Attention for scalable, instant 3D stylization without specialized training.

Findings

Outperforms existing methods in visual quality

Achieves higher computational efficiency

Ensures style consistency across multiple views

Abstract

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.