面向类别统一 3D 单目标跟踪的可泛化结构感知关键点对应
Generalizable Structure-Aware Keypoint Correspondence for Category-Unified 3D Single Object Tracking
提出自适应关键点提取与渐进式对应对齐模块，可复用于点云配准、3D 目标跟踪等需要跨帧几何关联的任务，解决类别统一模型下的尺度与结构变化问题。
原文依据 an adaptive keypoint extractor that produces scale-aware and semantically meaningful keypoints
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论点云中的 3D 单目标跟踪（SOT）对于现实世界的 3D 感知至关重要，但由于数据稀疏性以及不同物体类别间尺度和结构的巨大变化，该任务仍具挑战性。现有大多数方法依赖类别特定范式，即为每个类别训练单独的模型，严重限制了实际部署中的可扩展性和泛化能力。将这些方法扩展为能够跟踪多种物体类别的单一模型被证明是不充分的，因为类别间的显著差异使得在没有类别特定先验的情况下难以建立可靠的几何对应关系。为克服这些限制，我们提出了统一结构关键点跟踪器（UniKPT），一种用于类别统一 3D 点云跟踪的新型结构感知且可泛化的框架。UniKPT 包含三个关键模块：（1）自适应关键点提取器，生成尺度感知且语义有意义的关键点；（2）渐进式对应对齐器，建立鲁棒的跨帧几何关联；（3）置信度感知的结构定位模块，抑制不可靠匹配并利用细粒度结构关系进行精确 3D 定位。在 nuScenes 和 KITTI 基准上的大量实验表明，UniKPT 在类别统一 3D SOT 中达到了新的最优性能。在具有挑战性的 nuScenes 数据集上，我们的统一模型在 Success 和 Precision 指标上分别以 4.37% 和 5.16% 的优势超越了类别特定的最优跟踪器。
英文原文摘要 1549 字符
3D single object tracking (SOT) in point clouds is essential for real-world 3D perception, yet it remains challenging due to data sparsity and large variations in scale and structure across diverse object categories. Most existing methods rely on a category-specific paradigm that trains separate models for each class, severely limiting scalability and generalization in real deployment. Extending these methods to a single model capable of tracking diverse object categories proves inadequate, as the significant variations across categories make it difficult to establish reliable geometric correspondences without category-specific priors. To overcome these limitations, we propose a Unified Structural KeyPoint Tracker (UniKPT), a novel structure-aware and generalizable framework for category-unified 3D point cloud tracking. UniKPT comprises three key modules: (1) an adaptive keypoint extractor that produces scale-aware and semantically meaningful keypoints; (2) a progressive correspondence aligner that establishes robust cross-frame geometric associations; and (3) a confidence-aware structural localization module that suppresses unreliable matches and leverages fine-grained structural relationships for precise 3D localization. Extensive experiments on the nuScenes and KITTI benchmarks show that UniKPT achieves new state-of-the-art performance in category-unified 3D SOT. On the challenging nuScenes dataset, our unified model further surpasses category-specific state-of-the-art trackers by 4.37% in Success and 5.16% in Precision.