论文标题
从3D室内重建中学习3D语义场景图
Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions
论文作者
论文摘要
场景理解对计算机视觉引起了人们的兴趣。它不仅包括在场景中识别对象，还包括在给定上下文中的关系。有了这个目标，最近的一系列作品解决了3D语义细分和场景布局预测。在我们的工作中，我们专注于场景图，这是一个数据结构，该数据结构组织了图中场景的实体，其中对象是节点及其关系为边缘的关系。我们利用对场景图的推论，以此来进行3D场景理解，映射对象及其关系。特别是，我们提出了一种从场景的点云中回归场景图的学习方法。我们的新颖体系结构基于PointNet和Graph卷积网络（GCN）。此外，我们介绍了一个半自动生成的数据集3DSSG，其中包含3D场景的语义丰富的场景图。我们显示了我们在域 - 不合理的检索任务中的应用，其中图是3D-3D和2D-3D匹配的中间表示。
Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic segmentation and scene layout prediction. In our work we focus on scene graphs, a data structure that organizes the entities of a scene in a graph, where objects are nodes and their relationships modeled as edges. We leverage inference on scene graphs as a way to carry out 3D scene understanding, mapping objects and their relationships. In particular, we propose a learned method that regresses a scene graph from the point cloud of a scene. Our novel architecture is based on PointNet and Graph Convolutional Networks (GCN). In addition, we introduce 3DSSG, a semi-automatically generated dataset, that contains semantically rich scene graphs of 3D scenes. We show the application of our method in a domain-agnostic retrieval task, where graphs serve as an intermediate representation for 3D-3D and 2D-3D matching.
