基于边缘强化神经拉动模型的三维表面重建  

3D surface reconstruction method through neural-pull based on edge enhancement

作　　者：徐宝昌[1] 王毅豪 郝围围 尹士轩 王威 李雅飞 XU Baochang;WANG Yihao;HAO Weiwei;YIN Shixuan;WANG Wei;LI Yafei(College of Information Science and Engineering/College of Artificial Intelligence,China University of Petroleum,Beijing 102249,China;CNPC Engineering Technology R&D Company Limited,Beijing 102206,China)

机构地区：[1]中国石油大学(北京)信息科学与工程学院/人工智能学院,北京102249 [2]中国石油集团工程技术研究院有限公司钻井工艺研究所,北京102206

出　　处：《红外与激光工程》2024年第6期202-212,共11页Infrared and Laser Engineering

基　　金：国家自然科学基金项目(52374015);国家重点研发计划项目(2019YFA0708304)。

摘　　要：通过学习空间点云数据的符号距离函数(Signed Distance Functions, SDFs)进行三维表面重建是当前的研究热点。为重建出高精度的水密模型,神经拉动(Neural-pull, NP)采用点云拉动,以训练同步更新SDFs,但在实际重建过程中,重建模型会因为点云存在噪声和缺失而导致重建结果不够精细,带来错误的表面重建。针对以上问题,引入边缘提取强化输入点云的边缘信息,提出利用残差学习机制的边缘强化神经拉动模型(Neural Pull based on Edge Enhancement, NPEE)。为确保重建表面平滑的同时能够获取更多的表面细节,该方法在保留原本神经网络用于学习SDFs的基础上引入一个新的网络,利用残差学习机制学习点云的边缘SDFs。同时在原始点云的基础上,引入边缘因子σ,结合学习的边缘SDFs,通过点云边缘的鲁棒提取强化输入点云。为验证算法模型的优化效果,采用目前广泛使用的ABC数据集、斯坦福扫描模型和模拟扫描数据集设计对比实验,实验结果以及评估指标(CD)表明,NPEE可以有效改善神经拉动算法在边缘表面重建的缺陷,同时和其他重建方法相比,NPEE在面对稀疏点云和含噪点云时仍能保证重建的精确性和完整性。Objective Surface reconstruction refers to the process of reconstructing a continuous 3D surface from discrete spatial point clouds data.Learning signed distance functions(SDFs)of an object through spatial discrete point clouds to reconstruct the implicit surface of an object is currently the main research strategy.Neural-pull(NP)is a method to obtain high-quality SDFs from discrete point clouds information to reconstruct original surface.The key lies in using the predicted SDFs and the gradient information of the query point to pull the query point onto the reconstructed surface(Fig.1).The advantage of this method is that the model training process does not require ground truth(GT)SDFs as supervision,and at the same time,the signed distance value and gradient information are updated simultaneously during the training process.However,due to the inevitable noise and defects in the actually obtained point cloud data,NP will cause edge defects on the reconstructed surface during reconstruction.Therefore,in order to improve the reconstruction effect of the algorithm,solve the edge defects problem occurs in NP's sparse point clouds reconstruction,this paper proposes an improvement strategy,called neural-pull based on edge enhancement(NPEE).Methods In order to solve the NP edge overfitting problem,this paper proposes the NPEE framework(Fig.2).It consists of edge-construction network(EN)and NP network.EN(Fig.3)uses a residual learning mechanism to learn the edge SDFs of point clouds,ensuring sufficient edge accuracy while ensuring training efficiency.At the same time,based on the original point cloud,the edge factor is introduced,combined with the learned edge SDFs,to enhance the input point cloud through robust point cloud edge extraction(Fig.4).NPEE still retains the original neural network(Fig.5)for learning SDFs,so that the network that is prone to overfitting can obtain more surface details while ensuring the smoothness of the reconstructed surface.Results and Discussions Using the ABC data set,Stanford scanning mo

关 键 词：深度学习 三维点云 表面重建 符号距离函数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP391.9[自动化与计算机技术—计算机科学与技术]