基于改进Pix2Vox的单图像三维重建网络  

Improved Pix2Vox Based 3D Reconstruction Network from Single Image

作　　者：何鑫睿 李秀梅[1] 孙军梅[1] 李美玲[1] 袁珑 He Xinrui;Li Xiumei;Sun Junmei;Li Meiling;Yuan Long(School of Information Science and Technology,Hangzhou Normal University,Hangzhou 311121)

机构地区：[1]杭州师范大学信息科学与技术学院,杭州311121

出　　处：《计算机辅助设计与图形学学报》2022年第3期364-372,共9页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61801159,61571174);浙江省大学生科技创新活动计划(2021R426066)。

摘　　要：为进一步提升由单图像进行三维重建的精度,通过对Pix2Vox网络进行改进,提出一种基于深度学习的方法实现单图像三维重建的神经网络.首先,在Pix2Vox网络结构中增加多尺度连接和通道注意力机制,以保留多尺度信息,强化重点特征学习;其次,提出一个阈值计算模块,实现了适应不同类别的阈值设定方法,优化阈值取值;最后,提出一种融合型损失函数,融合模型的结构损失和类别损失,减小不平衡数据与类间差异对重建效果的影响.实验结果表明,该网络在公共数据集ShapeNet的13种模型类别上,平均IoU指标达到0.670,比Pix2Vox等网络取得了更好的单图像三维重建效果.In order to improve the accuracy of 3 D reconstruction from single image,a deep learning based neural network is proposed by improving the Pix2 Vox network for 3 D reconstruction from single image.Firstly,multi-scale connection and channel attention mechanism are added to the Pix2 Vox network structure to retain multi-scale information and enhance key feature learning.Secondly,a threshold calculation module is proposed to implement the threshold setting method adapted to different categories and optimize the threshold value.Finally,a fusion loss function is proposed to fuse the structural loss and the class loss of the model to reduce the influence of unbalanced data and class differences on the reconstruction effect.The experimental results show that the average IoU of the proposed network is 0.670 in the 13 model categories of ShapeNet dataset,indicating that better 3 D reconstruction performance can be achieved than using the Pix2 Vox and other networks.

关 键 词：三维重建 单幅图像 深度学习 注意力机制 损失函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]