基于上下文强化八叉树网络三维模型语义分割算法

针对三维模型语义分割中上下文特征的学习问题,提出了一种基于上下文强化八叉树网络的三维模型语义分割算法,名为CR-O-CNN(context-reinforced octree convolutional neural network).将基于八叉树的卷积神经网络引入上下文强化网络中,对上下文特征的学习过程进行马尔可夫决策过程的建模,并使用异步优势演员评论家算法对该过程进行优化,通过学习到深层的上下文特征,以提升三维模型的分割结果.在公共数据集ShapeNet上的实验结果表示,所提算法可提升三维模型语义分割的表现性能.

Semantic segmentation of 3D model based on context-reinforced octree network

Aiming at the learning of contextual features in 3D model semantic segmentation, this paper proposed a 3D model semantic segmentation algorithm based on context-reinforced octree network, named CR-O-CNN. The octree-based convolutional neural network combined the context reinforcement network to model Markov decision process of context feature learning, and used asynchronous advantage actor-critic to optimize the process. By learning deep context features, the segmentation results of the 3D model were improved. The experimental results on the public data set ShapeNet show that the proposed algorithm can improve the performance of semantic segmentation of 3D models.