arXiv 2602.006182026-01-31cs.CV

Tune-Your-Style: 可调强度的3D风格迁移与高斯点散布

Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting

School of Electronic and Computer Engineering, Peking University, Shenzhen, China（电子与计算机工程学院，北京大学深圳校区）；Pengcheng Laboratory, Shenzhen, China（鹏城实验室）；AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China（人工智能科学（AI4S）优选计划，北京大学深圳研究生院）；Department of Automation and BNRist, Tsinghua University, Beijing, China（自动化系和BNRist，清华大学，北京，中国）；Dalian University of Technology, China（大连理工大学）

Yian Zhao, Rushi Ye, Ruochong Zheng, Zesen Cheng, Chaoran Feng, Jiashu Yang, Pengchong Qiao, Chang Liu, Jie Chen

备注：: ICCV 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

Tune-Your-Style通过可调强度的3D风格迁移方法，实现灵活的内容-风格平衡，提升3D风格迁移的定制性。

摘要：

3D风格迁移指的是基于参考风格图像对3D资产进行艺术化处理。最近，基于3DGS的风格化方法受到广泛关注，主要得益于其显著提升的训练和渲染速度。然而，3D风格迁移面临的关键挑战是如何在内容和风格的模式与颜色之间取得平衡。尽管现有方法努力实现相对平衡的结果，但固定输出范式难以适应不同用户对内容-风格平衡的不同需求。在本工作中，我们引入了一种创新性的可调强度3D风格迁移范式，称为Tune-Your-Style，允许用户灵活调整注入到场景中的风格强度，以匹配其期望的内容-风格平衡，从而提升3D风格迁移的可定制性。为实现这一目标，我们首先引入高斯神经元，显式建模风格强度，并参数化一个可学习的风格调节器，以实现可调强度的风格注入。为了促进可调风格化的学习，我们进一步提出可调风格化指导，通过跨视角风格对齐从扩散模型中获取多视角一致的风格化视图，然后采用两阶段优化策略，通过调节来自风格化视图的完整风格指导和来自初始渲染的零风格指导之间的平衡，提供稳定且高效的指导。大量实验表明，我们的方法不仅能够产生视觉上吸引人的结果，还展示了3D风格迁移的灵活性和可定制性。项目页面可在https://zhao-yian.github.io/TuneStyle上查看。

英文摘要：

3D style transfer refers to the artistic stylization of 3D assets based on reference style images. Recently, 3DGS-based stylization methods have drawn considerable attention, primarily due to their markedly enhanced training and rendering speeds. However, a vital challenge for 3D style transfer is to strike a balance between the content and the patterns and colors of the style. Although the existing methods strive to achieve relatively balanced outcomes, the fixed-output paradigm struggles to adapt to the diverse content-style balance requirements from different users. In this work, we introduce a creative intensity-tunable 3D style transfer paradigm, dubbed \textbf{Tune-Your-Style}, which allows users to flexibly adjust the style intensity injected into the scene to match their desired content-style balance, thus enhancing the customizability of 3D style transfer. To achieve this goal, we first introduce Gaussian neurons to explicitly model the style intensity and parameterize a learnable style tuner to achieve intensity-tunable style injection. To facilitate the learning of tunable stylization, we further propose the tunable stylization guidance, which obtains multi-view consistent stylized views from diffusion models through cross-view style alignment, and then employs a two-stage optimization strategy to provide stable and efficient guidance by modulating the balance between full-style guidance from the stylized views and zero-style guidance from the initial rendering. Extensive experiments demonstrate that our method not only delivers visually appealing results, but also exhibits flexible customizability for 3D style transfer. Project page is available at https://zhao-yian.github.io/TuneStyle.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。