Hyperplane patch mixing-and-folding decoder and weighted chamfer distance loss for 3D point set reconstruction
Hyperplane patch mixing-and-folding decoder and weighted chamfer distance loss for 3D point set reconstruction
复制标题
DOI：
10.1007/s00371-022-02652-6
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
T. Furuya;Wujie Liu;Ryutarou Ohbuchi;Zhenzhong Kuang
中科院分区：
文献类型：
--
作者：
T. Furuya;Wujie Liu;Ryutarou Ohbuchi;Zhenzhong Kuang
三维点集重建是一项重要而又具有挑战性的三维形状分析任务。用于3D点集重建的当前最先进的算法采用具有编码器-解码器架构的深度神经网络（DNN）。最近，转换多个2D平面补丁以重建3D形状的解码器DNN已经取得了一些成功。这些“补丁折叠”解码器擅长于近似3D对象中的平滑表面。然而，由这些解码器生成的3D点集通常缺乏局部几何细节，因为2D平面贴片往往过度约束贴片折叠过程。在本文中，我们提出了一种新的解码器DNN的三维点集称为超平面混合和折叠网络（HMF-Net）。HMF-Net使用较少约束的超平面，而不是2D平面，面片作为折叠过程的输入。HMF-Net具有作为其核心构建块的标记混合层堆栈，以有效地学习超平面补丁之间的全局一致性。除了HMF-Net，我们还提出了一种新的损失三维点集重建称为加权倒角距离（WCD）。WCD试图通过强调生成的点集和地面实况点集之间较高的点对距离值，来加权或放大在训练样本中高度可变的形状部分的损失。这有助于解码器DNN更好地学习形状细节。我们全面评估我们的算法下三个三维点集重建的情况下，即，形状完成，形状上采样，从二维图像的形状重建。实验结果表明，我们的算法产生的精度高于现有的三维点集重建算法。
3D point set reconstruction is an important and challenging 3D shape analysis task. Current state-of-the-art algorithms for 3D point set reconstruction employ a deep neural network (DNN) having an encoder–decoder architecture. Recently, the decoder DNNs that transform multiple 2D planar patches to reconstruct a 3D shape have seen some success. These “patch-folding” decoders are adept at approximating smooth surfaces in 3D objects. However, 3D point sets generated by these decoders often lack local geometrical details, as 2D planar patches tend to overly constrain the patch folding process. In this paper, we propose a novel decoder DNN for 3D point sets calledHyperplane Mixing and Folding Net(HMF-Net). HMF-Net uses less constrainedhyperplane, not 2D plane, patches as its input to the folding process. HMF-Net has, as its core building block, a stack of token-mixing layers to effectively learn global consistency among the hyperplane patches. In addition to HMF-Net, we also propose a novel loss for 3D point set reconstruction calledWeighted Chamfer Distance(WCD). WCD tries to weight, or amplify, loss from parts of shape that are highly variable across training samples by emphasizing higher point-pair distance values between a generated point set and a groundtruth point set. This helps the decoder DNN learn shape details better. We comprehensively evaluate our algorithm under three 3D point set reconstruction scenarios, that are, shape completion, shape upsampling, and shape reconstruction from 2D images. Experimental results demonstrate that our algorithm yields accuracies higher than the existing algorithms for 3D point set reconstruction.