Scene understanding is a critical problem in computer vision. In this paper, we propose a 3D point-based scene graph generation ($\mathbf{SGG_{point}}$) framework to effectively bridge perception and reasoning to achieve scene understanding via three sequential stages, namely scene graph construction, reasoning, and inference. Within the reasoning stage, an EDGE-oriented Graph Convolutional Network ($\texttt{EdgeGCN}$) is created to exploit multi-dimensional edge features for explicit relationship modeling, together with the exploration of two associated twinning interaction mechanisms between nodes and edges for the independent evolution of scene graph representations. Overall, our integrated $\mathbf{SGG_{point}}$ framework is established to seek and infer scene structures of interest from both real-world and synthetic 3D point-based scenes. Our experimental results show promising edge-oriented reasoning effects on scene graph generation studies. We also demonstrate our method advantage on several traditional graph representation learning benchmark datasets, including the node-wise classification on citation networks and whole-graph recognition problems for molecular analysis.
翻译:场景理解是计算机视觉中的一个关键问题。 在本文中,我们提出了一个基于 3D 点的场景图生成( mathbf{ SGG ⁇ point $ $) 框架, 以有效地连接感知和推理, 通过三个相继阶段( 即 场景图构造、 推理和推理) 实现场景理解。 在推理阶段, 创建了以 EDGE 为主的场景图绘制网络( (\ textt{ EdgeGCN}$ ), 以利用多维边边特征进行明确的关系建模, 并探索两个相关的节点和边缘之间的双对齐互动机制, 以独立演化场图示。 总体而言, 我们的综合 $\ mathb{ SGGG ⁇ point $ $ 框架是为了寻找和推断真实世界和合成3D 点基场景所关注的场景结构。 我们的实验结果展示了景图绘制研究的面向边缘的推理效应。 我们还展示了我们的方法优势, 用于几个传统的图形代表学习基准数据集,, 包括引用网络的节点网络的节点分类以及分子分析的全图解识别识别识别识别问题。