SuperGSeg: 基于结构化超高斯的开放词汇3D分割
SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians
AI总结：
SuperGSeg通过结构化超高斯实现开放词汇3D分割，结合神经3D高斯体和语言特征蒸馏，提升场景理解与分割性能。
摘要：
3D高斯点散射最近因其高效的训练和实时渲染而受到关注。尽管其基本表示主要设计用于视图合成，但近期的研究将其扩展到场景理解，利用语言特征。然而，为每个高斯存储额外的高维特征对于语义信息是内存密集型的，这限制了它们在分割和解释具有挑战性的场景中的能力。为此，我们引入了SuperGSeg，一种新的方法，通过解耦分割和语言场蒸馏，促进连贯、上下文感知的层次场景表示。SuperGSeg首先利用神经3D高斯体从多视角图像中学习几何、实例和层次分割特征，借助现成的2D掩码。这些特征随后被用来创建稀疏的超高斯集合。超高斯有助于将2D语言特征提升和蒸馏到3D空间中。它们能够在中等GPU内存成本下实现层次场景理解，通过高维语言特征渲染。广泛的实验表明，SuperGSeg在开放词汇物体选择和语义分割任务上实现了显著的性能。
英文摘要：
3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While its vanilla representation is mainly designed for view synthesis, recent works extended it to scene understanding with language features. However, storing additional high-dimensional features per Gaussian for semantic information is memory-intensive, which limits their ability to segment and interpret challenging scenes. To this end, we introduce SuperGSeg, a novel approach that fosters cohesive, context-aware hierarchical scene representation by disentangling segmentation and language field distillation. SuperGSeg first employs neural 3D Gaussians to learn geometry, instance and hierarchical segmentation features from multi-view images with the aid of off-the-shelf 2D masks. These features are then leveraged to create a sparse set of \acrlong{superg}s. \acrlong{superg}s facilitate the lifting and distillation of 2D language features into 3D space. They enable hierarchical scene understanding with high-dimensional language feature rendering at moderate GPU memory costs. Extensive experiments demonstrate that SuperGSeg achieves remarkable performance on both open-vocabulary object selection and semantic segmentation tasks.
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。
