语义泡沫：统一空间与语义的场景分解
Semantic Foam: Unifying Spatial and Semantic Scene Decomposition
把 Radiant Foam 的 Voronoi 网格单元当作显式语义载体，用单元级特征场加空间正则来抑制遮挡与跨视角监督不一致造成的伪影，为基于显式空间划分的 3D 表示做物体级分割提供了可复用思路。
原文依据 integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现代场景重建方法（如 3D 高斯泼溅）能够以实时速度实现照片级真实感的新视角合成，但它们在交互式图形应用中的采用仍然有限。一个主要瓶颈在于，与传统的、由人工创作的 3D 资产相比，这类表示难以交互。尽管此前研究已尝试在这类模型上施加语义分解，但在分割质量与一致性方面仍存在显著挑战。为此，我们提出 Semantic Foam，将近期提出的 Radiant Foam 表示扩展到语义分解任务。我们的方法把 Radiant Foam 的 Voronoi 网格所具备的天然空间体分解与在单元层级参数化的显式语义特征场相结合。这种显式结构使得直接的空间正则化成为可能，从而避免由遮挡或跨视角监督不一致所引起的伪影——这些是其他基于点的表示常见的缺陷。实验结果表明，与 Gaussian Grouping 和 SAGA 等最优方法相比，我们的方法在物体级分割上取得了更优的性能。
英文原文摘要 1188 字符
Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the difficulty of interacting with these representations compared to traditional, human-authored 3D assets. While previous research has attempted to impose semantic decomposition on these models, significant challenges remain regarding segmentation quality and consistency. To address this, we introduce Semantic Foam, extending the recently proposed Radiant Foam representations to semantic decomposition tasks.Our approach integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level. This explicit structure enables direct spatial regularization, which prevents artifacts caused by occlusion or inconsistent supervision across views - common pitfalls for other point-based representations. Experimental results show that our method achieves superior object-level segmentation performance compared to state-of-the-art methods like Gaussian Grouping and SAGA.