论文标题
AKB-48：现实世界中的阐明对象知识库
AKB-48: A Real-World Articulated Object Knowledge Base
论文作者
论文摘要
人类的生活充满了铰接的物体。对铰接物体的全面理解，即外观，结构，物理特性和语义，将使许多研究社区受益。由于当前的铰接对象理解解决方案通常基于具有无物理属性的CAD模型的合成对象数据集，这阻止了视觉和机器人技术任务中的仿真到现实世界应用程序的概括。为了弥合差距，我们提出了AKB-48：一个大规模的铰接对象知识基础，由48个类别的2,037个现实世界3D铰接式对象模型组成。每个对象都由知识图Artikg描述。为了构建AKB-48，我们提出了快速的发音知识建模（FARM）管道，可以在10-15分钟内满足铰接式对象的Artikg，并在很大程度上降低了现实世界中对象建模的成本。使用我们的数据集，我们提出了Akbnet，这是一种用于类别级别视觉发音操纵（C-VAM）任务的新型积分管道，其中我们根据三个子任务为三个子任务，即构成估计，对象重建和操纵。数据集，代码和模型将在https://liuliu66.github.io/articulationBocts/上公开可用。
Human life is populated with articulated objects. A comprehensive understanding of articulated objects, namely appearance, structure, physics property, and semantics, will benefit many research communities. As current articulated object understanding solutions are usually based on synthetic object dataset with CAD models without physics properties, which prevent satisfied generalization from simulation to real-world applications in visual and robotics tasks. To bridge the gap, we present AKB-48: a large-scale Articulated object Knowledge Base which consists of 2,037 real-world 3D articulated object models of 48 categories. Each object is described by a knowledge graph ArtiKG. To build the AKB-48, we present a fast articulation knowledge modeling (FArM) pipeline, which can fulfill the ArtiKG for an articulated object within 10-15 minutes, and largely reduce the cost for object modeling in the real world. Using our dataset, we propose AKBNet, a novel integral pipeline for Category-level Visual Articulation Manipulation (C-VAM) task, in which we benchmark three sub-tasks, namely pose estimation, object reconstruction and manipulation. Dataset, codes, and models will be publicly available at https://liuliu66.github.io/articulationobjects/.
