基于卷积神经网络的人像浮雕建模与动画生成  

Portrait Relief Modeling and Animation Making through Convolutional Neural Networks

作　　者：罗萍 龙文斐 陈彦钊 周浩 张玉伟[1,2] Luo Ping;Long Wenfei;Chen Yanzhao;Zhou Hao;Zhang Yuwei(School of Mechanical&Automotive Engineering,Qilu University of Technology(Shandong Academy of Sciences),Ji’nan 250000;Industrial Engineering Technology Center,Shandong Institute of Mechanical Design and Research,Ji’nan 250000)

机构地区：[1]齐鲁工业大学(山东省科学院)机械与汽车工程学院,济南250000 [2]山东省机械设计研究院工业工程技术中心,济南250000

出　　处：《计算机辅助设计与图形学学报》2022年第9期1469-1476,共8页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(61772293)。

摘　　要：为克服传统人像浮雕设计专业性强、效率低、效果单一等不足,提出一种人像浮雕快速建模方法.首先基于法向相似原理构建人像浮雕合成数据集;然后建立卷积神经网络模型,实现2.5D高度场的快速压缩;最后对3D模型进行多视角连续采样,通过网络预测批量生成单帧浮雕模型,合成人像浮雕动画.在人像浮雕合成数据集上进行实验的结果表明,所提方法可以实现人像浮雕快速建模,建模效率高于传统方法;建模结果在定量分析指数PSNR方面优于同类方法,具有合理的深度层次,同时较好地保留了人脸细节特征;合成动画为3D人像提供了良好的浮雕艺术展示效果.To overcome the shortcomings of traditional portrait relief design,such as strong professional,low efficiency and single effect,a fast modeling method of portrait relief is proposed.First,a synthetic dataset is generated based on the principle of normal preservation.Then,a neural network is constructed and trained to automatically compress the height field.Finally,after sampling the 3D model from multiple viewing directions,a set of relief models are predicted through the network,then,the relief animation is synthesized.The experimental results on the synthetic portrait relief dataset show that the proposed method can generate portrait relief fast with higher efficiency than that of traditional methods.The modeling result is better than the similar methods in quantitative analysis index PSNR,which has reasonable depth level,and retains the detailed features of human face.The animation provides a novel artistic effect for portrait observation.

关 键 词：人像浮雕 浮雕动画 卷积神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]