深度学习在单图像三维模型重建的应用  

Application of deep learning to 3D model reconstruction of single image

作　　者：张豪 张强[2] 邵思羽[2] 丁海斌 ZHANG Hao;ZHANG Qiang;SHAO Siyu;DING Haibin(Graduate School,Air Force Engineering University,Xi’an Shannxi 710038,China;Air and Missile Defense College,Air Force Engineering University,Xi’an Shannxi 710038,China;Training Base,Army Engineering University of PLA,Xuzhou Jiangsu 221004,China)

机构地区：[1]空军工程大学研究生院,西安710038 [2]空军工程大学防空反导学院,西安710038 [3]陆军工程大学训练基地,江苏徐州221004

出　　处：《计算机应用》2020年第8期2351-2357,共7页journal of Computer Applications

基　　金：江苏省普通高校学术学位研究生科研创新计划项目(KYCX18_0072)。

摘　　要：针对基于单图像重建的三维模型具有高度不确定性问题,提出了一种基于深度图像估计、球面投影映射、三维对抗生成网络相结合的网络模型算法。首先,通过深度估计器得到输入图像的深度图像,这有利于对图像进一步的分析;其次,将得到的深度图像通过球面投影映射转换为三维模型;最后,利用三维对抗生成网络对重建的三维模型的真实性进行判断,建立更逼真的三维模型。理论分析和仿真实验表明,与学习先验知识生成三维模型的算法LVP相比,所提模型在真实三维模型与重建三维模型的交并比(IoU)上提高了20.1%,倒角距离(CD)缩小了13.2%。实验结果表明,所提模型在单视图三维模型重建中具有良好的泛化能力。To solve the problem that the reconstructed 3D model of a single image has high uncertainty,a network model based on depth image estimation,spherical projection mapping and 3D generative adversarial network was proposed.Firstly,the depth image of the input image was obtained by the depth estimator,which was helpful for the further analysis of the image.Secondly,the obtained depth image was converted into a 3D model by spherical projection mapping.Finally,3D generative adversarial network was utilized to judge the authenticity of the reconstructed 3D model,so as to obtain 3D model closer to reality.In the comparison experiments with LVP algorithm which learning view priors for 3D reconstruction,the proposed model has the Intersection-over-Union(IoU)increased by 20.1%and the Charmfer Distance(CD)decreased by 13.2%.Theoretical analysis and simulation results show that the proposed model has good generalization ability in the 3D model reconstruction of a single image.

关 键 词：深度图像 深度估计 三维重建 对抗生成网络 球面投影 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]