Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.10497 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911205943148544 |
|---|---|
| author | Ye, Yuteng Zhang, Zheng Zhang, Qinchuan Wang, Di Zhang, Youjia Zhang, Wenxiao Yang, Wei Liu, Yuan |
| author_facet | Ye, Yuteng Zhang, Zheng Zhang, Qinchuan Wang, Di Zhang, Youjia Zhang, Wenxiao Yang, Wei Liu, Yuan |
| contents | 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. Project page is available at: https://babahui.github.io/jigsaw3D.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10497 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking Ye, Yuteng Zhang, Zheng Zhang, Qinchuan Wang, Di Zhang, Youjia Zhang, Wenxiao Yang, Wei Liu, Yuan Computer Vision and Pattern Recognition 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. Project page is available at: https://babahui.github.io/jigsaw3D.github.io/ |
| title | Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Masking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.10497 |