基于环境信息挖掘的体素形变网络  

Voxel Deformation Network Based on Environmental Information Mining

作　　者：刘娜丽 田彦[1,3] 宋亚东 江腾飞 王勋 杨柏林[1] LIU Na-li;TIAN Yan;SONG Ya-dong;JIANG Teng-fei;WANG Xun;YANG Bai-lin(School of Computer Science&Information Engineering,Zhejiang Gongshang University,Hangzhou 310018,China;Zhejiang Lab,Hangzhou 311121,China;Shining 3D Research,Shining 3D Tech Co.,Ltd,Hangzhou 310013,China;School of Information Science Engineering,East China University of Science and Technology,Shanghai 200237,China)

机构地区：[1]浙江工商大学计算机与信息工程学院,杭州310018 [2]之江实验室,杭州311121 [3]先临三维科技股份有限公司研究院,杭州310013 [4]华东理工大学信息科学与工程学院,上海200237

出　　处：《计算机科学》2022年第10期207-213,共7页Computer Science

基　　金：国家重点研发计划(2018YFB1404102,2018YFB1403200);国家自然科学基金(61972351,61976188,61972353);浙江省自然科学基金(LY19F030005);北京航天航空大学开放课题基金(VRLAB2020B15);之江实验室资助项目(2019KD0AC02)。

摘　　要：3D形变技术是计算机图形学领域的研究热点之一。当前的3D形变方法主要通过聚合局部相邻的体素特征来学习物体形变前后的变化,未充分挖掘非局部体素特征之间的相互关系,这种环境信息的缺失导致模型无法捕获更具辨识性的特征。针对上述问题,设计了一种基于环境信息挖掘的体素形变网络,该网络能够同时对局部和环境信息进行提取,从不同的空间域中挖掘环境信息以提升网络的表征性能,进而建模物体形变前后的变化关系。引入自注意力机制,通过学习特征空间中不同体素的非局部依赖性,以提升体素特征的辨别力;引入一种多尺度分析方法,使用不同扩张率的空洞卷积分别提取不同感知域中的环境信息,为模型提供了更丰富的上下文特征。此外,文中分析了特征融合对模型的影响,并设计了一种基于编码器-解码器特征融合方法,自适应地对编码器和解码器提取的特征进行融合,提高了模型的非线性映射能力。在自建的齿科数据集上进行了充分的对比实验,结果表明,与现有方法相比,所提方法在形变预测任务的准确率上有一定的提升。The technique of 3 D deformation is one of the hot topics in the field of computer graphics.Current 3 D deformation methods mainly learn the changes before and after deformation by aggregating localized adjacent voxel features, and fail to exploit the interrelationship between non-local voxel features, and the absence of contextual information prevents the model from capturing more discriminative features.To address the above problems, this paper designs a voxel deformation network based on environmental information mining, which can extract local and environmental information simultaneously, and extract environmental information from different spatial domains to improve the representation performance of the network, further modeling the relationship before and after the deformation of the object.Firstly, a novel self-attention mechanism is introduced.Specifically, the learning of the non-local dependence of different voxels is proposed to improve the ability of voxel discrimination.Then, a multi-scale analysis method is introduced to extract environmental information in different perceptual fields via multiple dilated convolution with different dilation rates, which provides more informative contextual features for the subsequent models.In addition, this paper analyzes the impact of feature fusion on the model and designs a method based on encoder-decoder feature fusion, which adaptively fuses the features extracted from the encoder and decoder to improve the nonlinear mapping capability of the model.Extensive experiments are conducted on our tooth dataset.The results show that the deformation prediction accuracy of the proposed method is improved compared to existing methods.

关 键 词：形状变形 体素 注意力机制 特征融合 多尺度分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]