空间很重要：位置引导的 3D 指代表达分割
Spatial Matters: Position-Guided 3D Referring Expression Segmentation
把显式空间关系建模引入 3D 指代分割：用聚合局部上下文与空间关系的 point proxy 生成查询，并在解码器中用位置引导的可变形注意力逐步聚焦目标，可迁移到任何需要区分视觉相似实例的点云定位/分割任务。
原文依据 we design a position-guided deformable attention in the decoder, which progressively refines attention to concentrate on the target object
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D 指代表达分割（3D-RES）是一个新兴领域，其目标是根据给定的指代表达在点云场景中分割出三维物体。尽管现有方法已取得显著进展，但它们主要关注语义线索，往往忽略空间关系，而空间关系对于在复杂 3D 场景中分割所指代的物体至关重要，尤其是那些包含多个视觉相似实例的场景。本文提出 Position3D，一种将空间关系建模显式引入 3D-RES 的新方法。具体而言，我们引入一个空间感知的查询生成模块，通过聚合局部上下文并融入空间关系来构建点代理，并从中选出与文本最相关的点代理作为查询。此外，我们在解码器中设计了位置引导的可变形注意力，在位置关系的引导下逐步细化注意力以聚焦于目标物体。在两个基准数据集 ScanRefer 和 Multi3DRefer 上的大量实验验证了所提方法 Position3D 的有效性。
英文原文摘要 1115 字符
3D Referring Expression segmentation (3D-RES) is an emerging field that segments 3D objects in point cloud scenes based on given referring expressions. Although existing methods have achieved substantial progress, they primarily focus on semantic cues and often overlook spatial relations, which are essential for segmenting the referred objects in complex 3D scenes, especially those containing multiple visually similar instances. In this paper, we propose Position3D, a novel approach that explicitly incorporates spatial relation modeling into 3D-RES. Specifically, we introduce a spatial-aware query generation module that constructs point proxies by aggregating local context and incorporating spatial relations, from which the most text-relevant are selected as queries. Furthermore, we design a position-guided deformable attention in the decoder, which progressively refines attention to concentrate on the target object under positional relationship guidance. Extensive experiments on two benchmark datasets, i.e., ScanRefer, and Multi3DRefer, validate the effectiveness of the proposed method Position3D.