StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917248388562944 |
|---|---|
| author | Zhuang, Cailin Hu, Yaoqi Zhang, Xuanyang Cheng, Wei Bao, Jiacheng Liu, Shengqi Yang, Yiying Zeng, Xianfang Yu, Gang Li, Ming |
| author_facet | Zhuang, Cailin Hu, Yaoqi Zhang, Xuanyang Cheng, Wei Bao, Jiacheng Liu, Shengqi Yang, Yiying Zeng, Xianfang Yu, Gang Li, Ming |
| contents | Current 3D Gaussian Splatting stylization approaches are limited in their ability to represent diverse artistic styles, frequently defaulting to low-level texture replacement or yielding semantically inconsistent outputs. In this paper, we introduce StyleMe3D, a novel hierarchical framework that achieves comprehensive, high-fidelity stylization by disentangling multi-level style representations while preserving geometric fidelity. The cornerstone of StyleMe3D is Dynamic Style Score Distillation (DSSD), which harnesses latent priors from a style-aware diffusion model to provide high-level semantic guidance, ensuring robust and expressive style transfer. To further refine this distillation process, we propose a multi-modal alignment strategy using the CLIP latent space: a CLIP-based style stream evaluator (Contrastive Style Descriptor) that enforces middle-level stylistic similarity, and a CLIP-based content stream evaluator (3D Gaussian Quality Assessment) that acts as a global regularizer to mitigate typical GS quality degradation. Finally, a VGG-based Simultaneously Optimized Scale module is integrated to refine fine-grained texture details at the low-level. Extensive experiments demonstrate that our method consistently preserves intricate geometric details and achieves coherent stylistic effects across entire scenes, significantly surpassing state-of-the-art baselines in both qualitative and quantitative evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15281 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians Zhuang, Cailin Hu, Yaoqi Zhang, Xuanyang Cheng, Wei Bao, Jiacheng Liu, Shengqi Yang, Yiying Zeng, Xianfang Yu, Gang Li, Ming Computer Vision and Pattern Recognition Current 3D Gaussian Splatting stylization approaches are limited in their ability to represent diverse artistic styles, frequently defaulting to low-level texture replacement or yielding semantically inconsistent outputs. In this paper, we introduce StyleMe3D, a novel hierarchical framework that achieves comprehensive, high-fidelity stylization by disentangling multi-level style representations while preserving geometric fidelity. The cornerstone of StyleMe3D is Dynamic Style Score Distillation (DSSD), which harnesses latent priors from a style-aware diffusion model to provide high-level semantic guidance, ensuring robust and expressive style transfer. To further refine this distillation process, we propose a multi-modal alignment strategy using the CLIP latent space: a CLIP-based style stream evaluator (Contrastive Style Descriptor) that enforces middle-level stylistic similarity, and a CLIP-based content stream evaluator (3D Gaussian Quality Assessment) that acts as a global regularizer to mitigate typical GS quality degradation. Finally, a VGG-based Simultaneously Optimized Scale module is integrated to refine fine-grained texture details at the low-level. Extensive experiments demonstrate that our method consistently preserves intricate geometric details and achieves coherent stylistic effects across entire scenes, significantly surpassing state-of-the-art baselines in both qualitative and quantitative evaluations. |
| title | StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15281 |