arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.14048cs.CV
收藏

基于动态代码云的3D建模深度隐函数学习

Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Clouds

Tsinghua University(清华大学);JD Logistics(京东物流);Kuaishou Technology(快手科技);Wayne State University(韦恩州立大学)

Tianyang Li, Xin Wen, Yu-Shen Liu, Hua Su, Zhizhong Han

摘要:

深度隐式函数(Deep Implicit Function,DIF)作为一种高效的三维形状表示方法,已经得到了广泛的应用。为了捕获几何细节,当前的方法通常使用局部潜在代码来学习DIF,其将空间离散成规则的3D网格(或八叉树)并将局部代码存储在网格点(或八叉树节点)中。给定一个查询点,局部特征是通过插值其相邻的本地代码与他们的位置计算。然而,局部码被约束在离散和规则的位置,如网格点,这使得码的位置很难被优化,限制了它们的表示能力。为了解决这个问题,我们提出了使用动态代码云学习DIF,称为DCC-DIF。我们的方法显式地将本地代码与可学习的位置向量相关联,并且位置向量是连续的,可以动态优化,从而提高了表示能力。此外,我们提出了一种新的代码位置损失来优化代码位置,这将引导更多的本地代码分布在复杂的几何细节周围。与以前的方法相比,我们的DCC-DIF表示3D形状更有效地与少量的本地代码,并提高重建质量。实验表明,DCC-DIF实现了更好的性能比以前的方法。代码和数据可在https://github.com/lity20/DCCDIF上获得。

英文摘要:

Deep Implicit Function (DIF) has gained popularity as an efficient 3D shape representation. To capture geometry details, current methods usually learn DIF using local latent codes, which discretize the space into a regular 3D grid (or octree) and store local codes in grid points (or octree nodes). Given a query point, the local feature is computed by interpolating its neighboring local codes with their positions. However, the local codes are constrained at discrete and regular positions like grid points, which makes the code positions difficult to be optimized and limits their representation ability. To solve this problem, we propose to learn DIF with Dynamic Code Cloud, named DCC-DIF. Our method explicitly associates local codes with learnable position vectors, and the position vectors are continuous and can be dynamically optimized, which improves the representation ability. In addition, we propose a novel code position loss to optimize the code positions, which heuristically guides more local codes to be distributed around complex geometric details. In contrast to previous methods, our DCC-DIF represents 3D shapes more efficiently with a small amount of local codes, and improves the reconstruction quality. Experiments demonstrate that DCC-DIF achieves better performance over previous methods. Code and data are available at https://github.com/lity20/DCCDIF.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑