arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.16381cs.CV
收藏

自由形式描述引导的点云目标接地三维可视化图形网络

Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud

Xidian University(西安电子科技大学);Hunan University(湖南大学);The University of Western Australia(西澳大学)

Mingtao Feng, Zhen Li, Qi Li, Liang Zhang, XiangDong Zhang, Guangming Zhu, Hui Zhang, Yaonan Wang, Ajmal Mian

摘要:

3D对象接地旨在基于自由形式的语言描述在原始点云场景中定位最相关的目标对象。由于点云的不规则性和稀疏性,理解复杂多样的描述并将其直接提升为点云是一个新的具有挑战性的课题。3D对象接地主要有三个挑战:在复杂多样的描述中找到主要焦点;理解点云场景;定位目标对象。在本文中,我们将解决所有三个挑战。首先,我们提出了一个语言场景图模块来捕捉丰富的结构和长距离短语相关性。其次,我们引入了一个多层次的三维建议关系图模块来提取对象与对象、对象与场景的共现关系,增强了初始建议的视觉特征。最后,我们开发了一个描述引导的三维可视化图形模块,通过节点匹配策略对短语和建议的全局上下文进行编码。在具有挑战性的基准数据集(ScanRefer和Nr 3D)上进行的大量实验表明,我们的算法优于现有的最先进的算法。我们的代码可以在https://github.com/PNXD/FFL-3DOG上找到。

英文摘要:

3D object grounding aims to locate the most relevant target object in a raw point cloud scene based on a free-form language description. Understanding complex and diverse descriptions, and lifting them directly to a point cloud is a new and challenging topic due to the irregular and sparse nature of point clouds. There are three main challenges in 3D object grounding: to find the main focus in the complex and diverse description; to understand the point cloud scene; and to locate the target object. In this paper, we address all three challenges. Firstly, we propose a language scene graph module to capture the rich structure and long-distance phrase correlations. Secondly, we introduce a multi-level 3D proposal relation graph module to extract the object-object and object-scene co-occurrence relationships, and strengthen the visual features of the initial proposals. Lastly, we develop a description guided 3D visual graph module to encode global contexts of phrases and proposals by a nodes matching strategy. Extensive experiments on challenging benchmark datasets (ScanRefer and Nr3D) show that our algorithm outperforms existing state-of-the-art. Our code is available at https://github.com/PNXD/FFL-3DOG.

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。

↑