PV-Ground：文本引导的点-体素交互用于3D视觉定位
PV-Ground: Text-Guided Point-Voxel Interaction for 3D Visual Grounding
用体素骨干网络保留高分辨率空间细节，并用文本引导的关键点采样聚合特征，为3D视觉定位提供了一种避免激进下采样的点-体素交互范式。
原文依据 employs a voxel-based feature extraction backbone to preserve high-resolution spatial details, while utilizing compact keypoints to aggregate these features
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视觉定位（VG）旨在根据自由形式的文本描述在3D场景中定位目标物体。现有的3D VG模型主要采用基于点的骨干网络进行点云特征提取。这类方法需要对输入点云进行激进的下采样，从而牺牲了对精确定位至关重要的细粒度空间细节。本文提出PV-Ground，一种基于有效文本引导的点-体素特征交互的新型3D VG架构。我们的方法利用体素和关键点的互补优势：采用基于体素的特征提取骨干网络来保留高分辨率空间细节，同时利用紧凑的关键点聚合这些特征，以便与文本查询进行高效、深度的交互。此外，我们提出了一种文本引导的关键点采样模块，自适应地将关键点分布集中在文本描述的对象周围，从而实现任务特定的特征聚合，并显著提升模型性能。大量的定性和定量实验证明了我们方法的优越性。我们的方法在ScanRefer数据集上实现了5.1%的性能提升，在ReferIt3D数据集上提升了5.6%，同时在分割任务上也实现了超过4%的提升。代码将公开。
英文原文摘要 1344 字符
3D visual grounding (VG) aims to localize target objects in 3D scenes based on free-form textual descriptions. Existing 3D VG models predominantly employ point-based backbones for point cloud feature extraction. Such methods require aggressive downsampling of the input point cloud, which sacrifices the fine-grained spatial details crucial for precise localization. This paper proposes PV-Ground, a novel 3D VG architecture based on effective text-guided point-voxel feature interaction. Our method leverages the complementary strengths of both voxels and keypoints: it employs a voxel-based feature extraction backbone to preserve high-resolution spatial details, while utilizing compact keypoints to aggregate these features for efficient, deep interaction with the textual query. Furthermore, we propose a text-guided keypoint sampling module to adaptively concentrate the keypoint distribution around the text-described object, enabling task-specific feature aggregation and significantly boosts model performance. Extensive qualitative and quantitative experiments demonstrate the superiority of our proposed method. Our method achieves a performance improvement of 5.1% on the ScanRefer dataset and 5.6% on the ReferIt3D dataset, while also achieves over 4% improvement in the segmentation task. The code will be made publicly available.