PosEviLoc：基于位置条件的空间证据用于语言引导的三维定位

中文摘要 AI 辅助

基于语言的3D定位任务旨在根据附近物体及其空间关系的描述，检索包含目标位置的点云子图。现有方法通常将查询和子图压缩为全局描述符，这可能会模糊对象级语义和跨描述的空间一致性。我们提出了位置条件证据定位（PosEviLoc），一种查询位置感知的粗粒度文本到点云定位框架。PosEviLoc不依赖全局匹配，而是利用显式的语义和空间证据来评估每个候选子图。它将方向建模为由物体位置和假设查询位置共同决定的关系。由此产生的查询位置空间证据场（QSEF）衡量在每个假设位置得到支持的查询描述的比例，明确捕获它们的一致性，且无需使用真实查询姿态来构建证据场。多级证据读出（MER）将此证据总结为紧凑表示，由轻量级MLP转换为检索分数。在五个基准数据集上，PosEviLoc在Recall@1上平均比MNCL高出17个百分点。当用作即插即用的重排序器时，它使MNCL平均提升16个百分点。此外，PosEviLoc引入的参数明显更少，且推理速度比现有方法更快。

英文摘要

Language-based 3D localization retrieves the point-cloud submap containing a target position from descriptions of nearby objects and their spatial relations. Existing methods typically compress queries and submaps into global descriptors, potentially obscuring object-level semantics and cross-description spatial coherence. We propose Position-Conditioned Evidence Localization (PosEviLoc), a query-position-aware framework for coarse text-to-point-cloud localization. Instead of relying on global matching, PosEviLoc evaluates each candidate submap using explicit semantic and spatial evidence. It models direction as a relation jointly determined by an object position and a hypothetical query position. The resulting Query-Position Spatial Evidence Field (QSEF) measures the fraction of query descriptions supported at each hypothetical position, explicitly capturing their agreement without using the ground-truth query pose to construct the evidence field. A Multi-Level Evidence Readout (MER) summarizes this evidence in a compact representation, which a lightweight MLP converts into a retrieval score. Across five benchmarks, PosEviLoc outperforms MNCL by an average of 17 percentage points in Recall@1. When used as a plug-and-play reranker, it improves MNCL by an average of 16 percentage points. Moreover, PosEviLoc introduces substantially fewer parameters and achieves faster inference speed than existing methods.

发表机构

• Purdue University（普渡大学）
• Xi’an Jiaotong-Liverpool University（西交利物浦大学）
• Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））

机构由 AI 辅助整理，请以论文原文为准。