NormLift：从提升特征到三维高斯溅射中的语义可靠性

中文摘要 AI 辅助

免训练的加权聚合被广泛用于将二维语义特征提升到三维高斯上，以实现开放词汇场景理解，但其理论作用仍未被充分理解。现有分析通常从渲染侧论证该操作，将高斯特征视为可线性组合的欧几里得变量以重建二维特征图。然而，这一观点与下游三维使用方式不符，在下游中每个高斯通常在基于余弦的嵌入空间中被独立查询。我们从三维侧重新审视特征提升，并将每个高斯的分配问题表述为CLIP单位球上的余弦对齐问题。在该目标下，L2归一化的语义反投影特征成为闭式解，从每个高斯语义分配的角度为标准提升规则提供了补充解释。同一公式进一步将范数分解为视图内一致性和视图间一致性，表明特征幅值本身可作为语义可靠性信号。通过有效多视图支持进行校准，该可靠性分数引导一种模式投票细化，通过避免线性平均来保持CLIP特征有效性。在开放词汇三维语义分割上的实验表明，NormLift是一种高效、免训练的框架，在各种评估协议下均取得了强劲性能。

英文摘要

Training-free weighted aggregation is widely used to lift 2D semantic features onto 3D Gaussians for open-vocabulary scene understanding, yet its theoretical role remains insufficiently understood. Existing analyses typically justify this operation from the rendering side, treating Gaussian features as linearly composable Euclidean variables for reconstructing 2D feature maps. However, this view does not match downstream 3D usage, where each Gaussian is often queried independently in a cosine-based embedding space. We revisit feature lifting from the 3D side and formulate per-Gaussian assignment as a cosine alignment problem on the CLIP unit sphere. Under this objective, the L2-normalized semantic back-projected feature emerges as the closed-form solution, providing a complementary interpretation of the standard lifting rule from the perspective of per-Gaussian semantic assignment. The same formulation further yields a norm decomposition into intra-view and inter-view consistency, suggesting that feature magnitude itself can serve as a semantic reliability signal. Calibrated by effective multi-view support, this reliability score guides a mode-voting refinement that preserves CLIP feature validity by avoiding linear averaging. Experiments on open-vocabulary 3D semantic segmentation show that NormLift is an efficient, training-free framework that achieves strong performance across evaluation protocols.

发表机构

• King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

20 pages, 6 figures