arXiv 2606.267542026-06-26cs.CV

容量控制的多视图3D高斯泼溅风格化

Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting

Guangdong Provincial Key Laboratory of Visual Media and Multidimensional Intelligence, CSSE, Shenzhen University（广东省可视媒体与多维智能重点实验室，计算机科学与软件工程学院，深圳大学）；Tencent Games（腾讯游戏）；The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Tel Aviv University（特拉维夫大学）

Zhihao Wen, Yixin Yang, Bojian Wu, Yang Zhou, Dani Lischinski, Daniel Cohen-Or, Hui Huang

备注：: Accepted to ECCV 2026. Project page: https://vcc2310.github.io/SceneStyler/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出基于最优传输的容量控制框架，通过半平衡最优传输和列容量约束解决多视图风格分配不稳定问题，实现跨视图一致的3D风格化。

摘要：

虽然3D高斯泼溅（3DGS）为新视图合成提供了高效且显式的表示，但强制跨视图的风格一致性仍然具有挑战性。现有的3D风格化方法通常对每个渲染视图独立应用2D特征匹配损失，这导致不稳定的风格分配、多对一特征重用以及有限的跨视图一致性。我们提出了一种基于最优传输的容量控制框架，用于3DGS的多视图风格化。具体来说，我们将局部风格匹配重新表述为半平衡最优传输问题。通过引入具有可调强度的显式列容量约束，我们的公式减轻了多对一匹配，并实现了风格特征的可控分配。这种基于传输的目标提供了一种原则性机制，用于平衡特征覆盖和风格多样性，同时保持跨视图的稳定对应关系。为了进一步增强跨视图一致性，我们引入了一种新颖的跨视图匹配引导，以约束场景内容与风格模式之间的对应关系。此外，我们引入了若干几何正则化来增强原始3DGS，从而使优化的高斯基元能够在风格化过程中表示更细粒度的纹理。大量实验表明，我们的方法显著提高了多视图风格一致性，并产生了稳定、富有表现力的3D风格化，同时保留了场景的核心语义结构。

英文摘要：

While 3D Gaussian Splatting (3DGS) provides an efficient and explicit representation for novel view synthesis, enforcing stylistic coherence across viewpoints remains challenging. Existing 3D stylization methods typically apply 2D feature-matching losses independently per rendered view, which leads to unstable style allocation, many-to-one feature reuse, and limited cross-view consistency. We propose a capacity-controlled framework for multi-view stylization of 3DGS, grounded in optimal transport. Specifically, we reformulate local style matching as a semi-balanced optimal transport problem. By introducing explicit column-capacity constraints with tunable strength, our formulation mitigates many-to-one matching and enables controllable allocation of style features. This transport-based objective provides a principled mechanism for balancing feature coverage and stylistic diversity while maintaining stable correspondences across viewpoints. To further enhance cross-view coherence, we incorporate a novel cross-view matching guidance to constrain correspondences between scene content and style patterns. In addition, we introduce several geometric regularizations to enhance the vanilla 3DGS, thereby enabling optimized Gaussian primitives to represent finer-grained textures during stylization. Extensive experiments demonstrate that our approach significantly improves multi-view stylistic consistency and produces stable, expressive 3D stylizations while preserving the core semantic structure of the scene.

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。