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 prevalent 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—spatial shuffling and random masking of reference patches—to suppress object semantics and isolate 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.
Our jigsaw-based approach generates seamless tileable textures without seam artifacts, outperforming traditional methods like Blender.
Jigsaw3D infers and applies globally consistent styles from partial reference images, demonstrating robust style understanding.
Our method maintains structural integrity and multi-view consistency while transferring artistic styles to complex architectural scenes.
Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking
@article{ye2024jigsaw3d,
author = {Ye, Yuteng and Zhang, Zheng and Zhang, Qinchuan and Wang, Di and Zhang, Youjia and Zhang, Wenxiao and Yang, Wei and Liu, Yuan},
title = {Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking},
journal = {arXiv preprint},
year = {2025},
}