arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.04725cs.CVcs.AI
收藏

学习3D形状生成和匹配的基本结构

Learning elementary structures for 3D shape generation and matching

LIGM (UMR 8049), École des Ponts, UPE(LIGM(UMR 8049),巴黎东大桥梁学院);Adobe Research(奥多比研究院)

Theo Deprelle, Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry

摘要:

我们建议将形状表示为可学习的基本3D结构的变形和组合,这些结构是通过形状集合训练产生的图元。我们证明了学习的基本3D结构导致3D形状生成和匹配的明显改善。更确切地说,我们提出了两种互补的方法来学习基本结构:(i)补丁变形学习和(ii)点平移学习。这两种方法都可以扩展到更高维度的抽象结构,以改善结果。我们在两个任务上评估我们的方法:重建ShapeNet对象和估计人类扫描之间的密集对应关系(FAUST内部挑战)。我们显示出16%的改进,表面变形方法的形状重建和优于FAUST间的挑战国家的最先进的6%。

英文摘要:

We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape. We demonstrate that the learned elementary 3D structures lead to clear improvements in 3D shape generation and matching. More precisely, we present two complementary approaches for learning elementary structures: (i) patch deformation learning and (ii) point translation learning. Both approaches can be extended to abstract structures of higher dimensions for improved results. We evaluate our method on two tasks: reconstructing ShapeNet objects and estimating dense correspondences between human scans (FAUST inter challenge). We show 16% improvement over surface deformation approaches for shape reconstruction and outperform FAUST inter challenge state of the art by 6%.

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。

↑