M2StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910103065591808 |
|---|---|
| author | Miao, Xingyu Qiu, Xueqi Duan, Haoran Huang, Yawen Wu, Xian Deng, Jingjing Long, Yang |
| author_facet | Miao, Xingyu Qiu, Xueqi Duan, Haoran Huang, Yawen Wu, Xian Deng, Jingjing Long, Yang |
| contents | Conventional 3D style transfer methods rely on a fixed reference image to apply artistic patterns to 3D scenes. However, in practical applications such as virtual or augmented reality, users often prefer more flexible inputs, including textual descriptions and diverse imagery. In this work, we introduce a novel real-time styling technique M2StyleGS to generate a sequence of precisely color-mapped views. It utilizes 3D Gaussian Splatting (3DGS) as a 3D presentation and multi-modality knowledge refined by CLIP as a reference style. M2StyleGS resolves the abnormal transformation issue by employing a precise feature alignment, namely subdivisive flow, it strengthens the projection of the mapped CLIP text-visual combination feature to the VGG style feature. In addition, we introduce observation loss, which assists in the stylized scene better matching the reference style during the generation, and suppression loss, which suppresses the offset of reference color information throughout the decoding process. By integrating these approaches, M2StyleGS can employ text or images as references to generate a set of style-enhanced novel views. Our experiments show that M2StyleGS achieves better visual quality and surpasses the previous work by up to 32.92% in terms of consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03773 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | M2StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting Miao, Xingyu Qiu, Xueqi Duan, Haoran Huang, Yawen Wu, Xian Deng, Jingjing Long, Yang Computer Vision and Pattern Recognition Conventional 3D style transfer methods rely on a fixed reference image to apply artistic patterns to 3D scenes. However, in practical applications such as virtual or augmented reality, users often prefer more flexible inputs, including textual descriptions and diverse imagery. In this work, we introduce a novel real-time styling technique M2StyleGS to generate a sequence of precisely color-mapped views. It utilizes 3D Gaussian Splatting (3DGS) as a 3D presentation and multi-modality knowledge refined by CLIP as a reference style. M2StyleGS resolves the abnormal transformation issue by employing a precise feature alignment, namely subdivisive flow, it strengthens the projection of the mapped CLIP text-visual combination feature to the VGG style feature. In addition, we introduce observation loss, which assists in the stylized scene better matching the reference style during the generation, and suppression loss, which suppresses the offset of reference color information throughout the decoding process. By integrating these approaches, M2StyleGS can employ text or images as references to generate a set of style-enhanced novel views. Our experiments show that M2StyleGS achieves better visual quality and surpasses the previous work by up to 32.92% in terms of consistency. |
| title | M2StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.03773 |