为了解决弱纹理重建难、资源消耗大和重建时间长等问题,提出了一种基于自适应聚合循环递归卷积的多阶段稠密点云重建网络,即A2R2-MVSNet(adaptive aggregation recurrent recursive multi view stereo net).该方法首先引入一种基于多尺度循环递归残差的特征提取模块,聚合上下文语义信息,以解决弱纹理或无纹理区域特征提取难的问题.在代价体正则化部分,提出一种残差正则化模块,该模块在略微增加内存消耗的前提下,提高了 3D CNN提取和聚合上下文语意的能力.实验结果表明,提出的方法在 DTU数据集上的综合指标排名靠前,在重建细节上有着更好的体现,且在BlendedMVS数据集上生成了不错的深度图和点云结果,此外网络还在自采集的大规模高分辨率数据集上进行了泛化测试.归功于由粗到细的多阶段思想和我们提出的模块,网络在生成高准确性和完整性深度图的同时,还能进行高分辨率重建以适用于实际问题.
Dense point cloud reconstruction network based on adaptive aggregation recurrent recursion
To address the problems such as difficulties in weak texture reconstruction,high resource consumption,and long reconstruction time,a multi-stage dense point cloud reconstruction network based on adaptive aggregation cyclic recursive convolution was proposed,namely A2R2-MVSNet(adaptive aggregation recurrent recursive multi view stereo net).This method first introduced a feature extraction module based on multi-scale cyclic recursive residuals to aggregate contextual semantic information,addressing the problem of difficult feature extraction in weakly textured or textureless regions.In the cost body regularization part,a residual regularization module was proposed.This module enhanced the ability of 3D CNN to extract and aggregate contextual semantics under the premise of slightly increasing memory consumption.The experimental results demonstrated that the proposed method ranked high in comprehensive metrics on the DTU dataset,showcasing superior performance in reconstructing details.Additionally,it could generate good depth maps and point cloud results on the BlendedMVS dataset.Furthermore,the network was tested for generalization on self-collected large-scale high-resolution datasets.Thanks to the coarse-to-fine multi-stage idea and our proposed module,the network could not only generate high-accuracy and complete depth maps,but also perform high-resolution reconstructions suitable for practical applications.
deep learningcomputer vision3D reconstructiondense reconstructionmulti-view stereorecurrent neural network
NETL
NSTL
万方数据
