Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking

Yuteng Ye, Zhangzheng, Qinchuan Zhang, Di Wang, Youjia Zhang, Wenxiao ZHANG, Wei Yang, Yuan Liu

Keywords: 3D Stylization, Jigsaw Operation, Style-Semantic Disentanglement

Abstract: Controllable 3D style transfer seeks to restyle a 3D asset so that its textures match a reference image while preserving the integrity and multi-view consistency. The pravelent methods either rely on direct reference style token injection or score-distillation from 2D diffusion models, which incurs heavy per-scene optimization and often entangles style with semantic content. We introduce Jigsaw3D, a multi-view diffusion based pipeline that decouples style from content and enables fast, view-consistent stylization. Our key idea is to leverage the jigsaw operation—random spatial shuffling of reference patches—to suppresses object semantics and isolates stylistic statistics (color palettes, strokes, textures). We integrate these style cues into a multi-view diffusion model via reference-to-view cross-attention, producing view-consistent stylized renderings conditioned on the input mesh. The renders are then style-baked onto the surface to yield seamless textures. Across standard 3D stylization benchmarks, Jigsaw3D achieves high style fidelity and multi-view consistency with substantially lower latency, and generalizes to masked partial reference stylization, multi-object scene styling, and tileable texture generation.

Primary Area: generative models

Submission Number: 4951