3D-SPS：基于指涉点渐进选择的单阶段3D视觉定位
3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
AI总结：
提出3D-SPS单阶段方法，通过语言引导的指涉点渐进选择，直接定位3D点云中的目标对象，在ScanRefer和Nr3D/Sr3D数据集上取得最优性能。
摘要：
3D视觉定位旨在根据自由形式的语言描述，在3D点云场景中定位所指的目标对象。以往的方法大多遵循两阶段范式，即与语言无关的检测和跨模态匹配，这种范式受限于其分离的架构。在该范式中，由于3D点云固有的特性（不规则且规模大），检测器需要从原始点云中采样关键点，为每个关键点生成相应的对象提议。然而，稀疏的提议可能在检测中遗漏目标，而密集的提议则可能混淆匹配模型。此外，与语言无关的检测阶段只能采样目标上的一小部分关键点，导致目标预测性能下降。本文提出了一种3D单阶段指涉点渐进选择（3D-SPS）方法，该方法在语言的引导下逐步选择关键点，并直接定位目标。具体而言，我们提出了一个描述感知关键点采样（DKS）模块，用于粗略聚焦于与语言相关的对象的点，这些点是定位的重要线索。此外，我们设计了一个目标导向的渐进挖掘（TPM）模块，通过渐进式模态内关系建模和模态间目标挖掘，精细地聚焦于目标的点。3D-SPS弥合了3D视觉定位任务中检测与匹配之间的差距，在单阶段中实现目标定位。实验表明，3D-SPS在ScanRefer和Nr3D/Sr3D数据集上均达到了最先进的性能。
英文摘要：
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description. Previous methods mostly follow a two-stage paradigm, i.e., language-irrelevant detection and cross-modal matching, which is limited by the isolated architecture. In such a paradigm, the detector needs to sample keypoints from raw point clouds due to the inherent properties of 3D point clouds (irregular and large-scale), to generate the corresponding object proposal for each keypoint. However, sparse proposals may leave out the target in detection, while dense proposals may confuse the matching model. Moreover, the language-irrelevant detection stage can only sample a small proportion of keypoints on the target, deteriorating the target prediction. In this paper, we propose a 3D Single-Stage Referred Point Progressive Selection (3D-SPS) method, which progressively selects keypoints with the guidance of language and directly locates the target. Specifically, we propose a Description-aware Keypoint Sampling (DKS) module to coarsely focus on the points of language-relevant objects, which are significant clues for grounding. Besides, we devise a Target-oriented Progressive Mining (TPM) module to finely concentrate on the points of the target, which is enabled by progressive intra-modal relation modeling and inter-modal target mining. 3D-SPS bridges the gap between detection and matching in the 3D visual grounding task, localizing the target at a single stage. Experiments demonstrate that 3D-SPS achieves state-of-the-art performance on both ScanRefer and Nr3D/Sr3D datasets.
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。
