Multi-view based neural network for semantic segmentation on 3D scenes  

作　　者：Yonghua LU Mingmin ZHEN Tian FANG 

机构地区：[1]School of Resource and Environmental Sciences,Wuhan University,Wuhan 430072,China [2]Department of Computer Science and Engineering,The Hong Kong University of Science and Technology,Hong Kong,China

出　　处：《Science China(Information Sciences)》2019年第12期216-218,共3页中国科学（信息科学）（英文版）

基　　金：supported by GRF(Grant No.16203518);Hong Kong RGC(Grant Nos.16208614,T22-603/15N);Hong Kong ITC(Grant No.PSKL12EG02);National Basic Research Program of China(973 Program)(Grant No.2012CB316300)

摘　　要：Dear editor,For semantic segmentation tasks,convolutional neural net work(CNN)based methods have been prevalent for both 2D image semantic segmentation and 3D semantic segmentation.Though traditional methods often use local features to segment a target(For example,in[1]both 2D local features and 3D local features are used to boost recognition ability),CNN based methods[2,3]exhibit much better performance than traditional methods[4].In all the CNN based methods on images,fully convolutional networks(FCNs)[2]are firstly proposed for end-to-end training.Basically,all the following methods are the variants of FCNs.For 3D input,some studies leverage 3D convolution to predict dense 3D semantic voxel maps[5].However,3D convolution has the limitation of low resolution as the GPU memory constraint.Additionally,RGB information is not well considered though it is very important.As semantic segmentation on images has been very good,we can project the semantic segmentation results of images to 3D mesh based on the geometrie relationship.In this study,we mainly exploit the multi-view based neural network for semantic segmentation on 3D scenes.

关 键 词：NEURAL Basic EDITOR 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]