3DWG：基于类别与实例级对齐的三维弱监督视觉定位
3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment
AI总结：
本文提出3DWG方法，通过类别级和实例级对齐分支分别利用预训练检测器类别知识与语言空间关系描述，解决三维弱监督视觉定位中的类别歧义和实例干扰问题，在Nr3D、Sr3D和ScanRef上取得最优性能。
摘要：
三维弱监督视觉定位任务旨在基于自然语言描述在点云中定位有向三维边界框，而无需标注来引导模型学习。该设置面临两个主要挑战：类别级歧义和实例级复杂性。类别级歧义源于以高度稀疏的点云格式表示细粒度类别的对象，使得类别区分变得困难。实例级复杂性源于同一类别的多个实例共存于一个场景中，导致定位过程中的干扰。为了解决这些挑战，我们提出了一种新颖的弱监督定位方法，该方法明确区分类别和实例。在类别级分支中，我们利用来自预训练外部检测器的大量类别知识，将对象提议特征与句子级类别特征对齐，从而增强类别感知能力。在实例级分支中，我们利用语言查询中的空间关系描述来细化对象提议特征，确保对象之间的清晰区分。这些设计使我们的模型能够准确识别目标类别的对象，同时区分同一类别内的实例。与先前方法相比，我们的方法在三个广泛使用的基准数据集Nr3D、Sr3D和ScanRef上取得了最先进的性能。
英文摘要：
The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges: category-level ambiguity and instance-level complexity. Category-level ambiguity arises from representing objects of fine-grained categories in a highly sparse point cloud format, making category distinction challenging. Instance-level complexity stems from multiple instances of the same category coexisting in a scene, leading to distractions during grounding. To address these challenges, we propose a novel weakly-supervised grounding approach that explicitly differentiates between categories and instances. In the category-level branch, we utilize extensive category knowledge from a pre-trained external detector to align object proposal features with sentence-level category features, thereby enhancing category awareness. In the instance-level branch, we utilize spatial relationship descriptions from language queries to refine object proposal features, ensuring clear differentiation among objects. These designs enable our model to accurately identify target-category objects while distinguishing instances within the same category. Compared to previous methods, our approach achieves state-of-the-art performance on three widely used benchmarks: Nr3D, Sr3D, and ScanRef.
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。
