论文阅读：Multi-view Convolutional Neural Networks for 3D Shape Recognition_upright orientation of 3d shapes with convolutiona-CSDN博客

网友收藏2024-01-25 05:06

链接地址：https://blog.csdn.net/u010167269/article/details/51498927
链接标题：论文阅读：Multi-view Convolutional Neural Networks for 3D Shape Recognition_upright orientation of 3d shapes with convolutiona-CSDN博客
所属网站：blog.csdn.net
被收藏次数：6190

文章浏览阅读2.3w次，点赞27次，收藏94次。阅读一篇ICCV2015的论文：Multi-view Convolutional Neural Networks for 3D Shape Recognition，简称：MVCNN 用物体的三维数据从不同“视角”所得到的二维图，作为原始的训练数据。通过View-pooling层，聚合特征。再通过经典的二维图像卷积网络进行训练，训练出的模型，对三维物体的识别、分类效果之好，比那些用三维数据直接训练出的模型好很多。_upright orientation of 3d shapes with convolutional networks

本文地址：https://tebull.com/detail/577550.html

标签：upright orientation of 3d shapes with convolutional networks