M$^2$StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting


Xingyu Miao (Durham University), Xueqi Qiu (Durham University), Haoran Duan (Tsinghua University), Yawen Huang (Tencent Jarvis Lab), Xian Wu (Tencent Jarvis Lab), Jingjing Deng (University of Bristol), Yang Long (Durham University)
The 35th British Machine Vision Conference

Abstract

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 M$^2$StyleGS 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. M$^2$StyleGS 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, M$^2$StyleGS can employ text or images as references to generate a set of style-enhanced novel views. Our experiments show that M$^2$StyleGS achieves better visual quality and surpasses the previous work by up to 32.92\% in terms of consistency.

Citation

@inproceedings{Miao_2025_BMVC,
author    = {Xingyu Miao and Xueqi Qiu and Haoran Duan and Yawen Huang and Xian Wu and Jingjing Deng and Yang Long},
title     = {M$^2$StyleGS: Multi-Modality 3D Style Transfer with Gaussian Splatting},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_133/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection