Lu Jian

Understanding the implication of point cloud is still challenging in the aim of classification or segmentation for point cloud due to its irregular and sparse structure. As we have known, PointNet architecture as a ground-breaking work for point cloud process can learn shape features directly on unordered 3D point cloud and has achieved favorable performance, such as 86% mean accuracy and 89.2% overall accuracy for classification task, respectively. However, this model fails to consider the fine-grained semantic information of local structure for point cloud. Then, a multiscale receptive fields graph attention network by means of semantic features of local patch for point cloud is proposed in this paper, and the learned feature map for our network can well capture the abundant features information of point cloud. The proposed MRFGAT architecture is tested on ModelNet datasets, and results show it achieves state-of-the-art performance in shape classification tasks, such as it outperforms GAPNet model by 0.1% in terms of OA and compete with DGCNN model in terms of MA.

There is life, there life "risk." Because life in the "body" exists in the way of life of the "suffering" in essence is the body's "suffering." Life, "suffering" from the birth of life "laws" and life itself for the existence of "goods", "name", "Road" and "goods", "name" is not only the guardian of life, or destruction of life were. Life on the Road to resist, the "goods", "name" of the competition is bound to lead to punishment Road, resulting in life between the carnage. Get rid of life, "suffering," preserve the life of the "body", it is obedience Road will, willing to accept the road to give life to all; eradication of life to survive, the survival on the desire to get rid of "goods", "name" entangled, while the world to follow, "no to born."