arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.05558cs.CV
收藏

基于点的三维场景图分析中的面向边缘推理

Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis

University of Sydney(悉尼大学);University of New South Wales(新南威尔士大学)

Chaoyi Zhang, Jianhui Yu, Yang Song, Weidong Cai

摘要:

场景理解是计算机视觉中的一个关键问题。在本文中,我们提出了一个三维点为基础的场景图生成($\mathbf{SGG_{point}}$)框架,有效地桥梁感知和推理,实现场景理解通过三个连续的阶段,即场景图的建设,推理,推理。在推理阶段,一个面向边缘的图卷积网络($\texttt{EdgeGCN}$)创建利用多维边缘特征显式关系建模,以及探索两个相关的孪生交互机制之间的节点和边缘的场景图表示的独立进化。总的来说,我们的集成$\mathbf{SGG_{point}}$框架的建立,寻求和推断感兴趣的场景结构,从现实世界和合成的3D基于点的场景。我们的实验结果表明,有前途的面向边缘的推理效果场景图生成研究。我们还在几个传统的图表示学习基准数据集上展示了我们的方法优势,包括引文网络上的节点分类和分子分析的全图识别问题。

英文摘要:

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.

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。

↑