GeoGuide：面向开放词表 3D 语义分割的分层几何引导
GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation
用预训练 3D 模型自身的几何先验替代对 2D 开放词表模型的单向蒸馏，通过超点级不确定性加权和实例级掩码重建抑制 2D 噪声，为 3D 开放词表分割提供了一条不牺牲几何表征的路线。
原文依据 aligning 3D features to the 2D representation space restricts intrinsic 3D geometric learning and inherits errors from 2D predictions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论开放词表 3D 语义分割旨在分割训练集之外的任意类别。现有方法主要依赖从 2D 开放词表模型蒸馏知识。然而，将 3D 特征对齐到 2D 表示空间会限制 3D 内在几何的学习，并继承 2D 预测中的误差。为解决这些局限，我们提出 GeoGuide，一个利用预训练 3D 模型整合分层几何—语义一致性的新框架，用于开放词表 3D 分割。具体而言，我们引入基于不确定性的超点蒸馏模块，融合几何与语义特征以估计逐点不确定性，在超点内自适应地加权 2D 特征，从而在抑制噪声的同时保留判别性信息，增强局部语义一致性。此外，我们的实例级掩码重建模块利用几何先验，通过重建完整实例掩码来强化实例内部的语义一致性。另外，我们的实例间关系一致性模块对齐几何与语义相似度矩阵，以校准同类物体跨实例的一致性，缓解视角引起的语义漂移。在 ScanNet v2、Matterport3D 和 nuScenes 上的大量实验证明了 GeoGuide 的优越性能。
英文原文摘要 1361 字符
Open-vocabulary 3D semantic segmentation aims to segment arbitrary categories beyond the training set. Existing methods predominantly rely on distilling knowledge from 2D open-vocabulary models. However, aligning 3D features to the 2D representation space restricts intrinsic 3D geometric learning and inherits errors from 2D predictions. To address these limitations, we propose GeoGuide, a novel framework that leverages pretrained 3D models to integrate hierarchical geometry-semantic consistency for open-vocabulary 3D segmentation. Specifically, we introduce an Uncertainty-based Superpoint Distillation module to fuse geometric and semantic features for estimating per-point uncertainty, adaptively weighting 2D features within superpoints to suppress noise while preserving discriminative information to enhance local semantic consistency. Furthermore, our Instance-level Mask Reconstruction module leverages geometric priors to enforce semantic consistency within instances by reconstructing complete instance masks. Additionally, our Inter-Instance Relation Consistency module aligns geometric and semantic similarity matrices to calibrate cross-instance consistency for same-category objects, mitigating viewpoint-induced semantic drift. Extensive experiments on ScanNet v2, Matterport3D, and nuScenes demonstrate the superior performance of GeoGuide.