arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11622cs.CVcs.CGcs.GRcs.LGstat.ML
收藏

基于CFAN-VAE的曲面无监督几何去纠缠

Unsupervised Geometric Disentanglement for Surfaces via CFAN-VAE

Rensselaer Polytechnic Institute(伦斯勒理工学院)

N. Joseph Tatro, Stefan C. Schonsheck, Rongjie Lai

摘要:

几何解纠缠,内在(即身份)和外在(即姿态)几何的潜在代码的分离,是非欧几里德数据的生成模型,如3D可变形模型的一个突出任务。它为潜在空间提供了更大的可解释性,并导致了对生成的更多控制。这项工作介绍了一个网格功能,共形因子和正常功能(CFAN),用于网格卷积自动编码器。我们进一步提出CFAN-VAE,一种新的架构,解开身份和构成使用CFAN功能。CFAN-VAE在训练过程中不需要身份或姿态的标签信息,以无监督的方式实现几何解纠缠。我们的综合实验,包括重建,插值,生成和身份/姿态转移,证明CFAN-VAE实现了最先进的性能无监督的几何解纠缠。我们还成功地检测到网格卷积自动编码器中的几何解纠缠水平,该编码器通过将其潜在空间注册到CFAN-VAE的潜在空间来直接编码xyz坐标。

英文摘要:

Geometric disentanglement, the separation of latent codes for intrinsic (i.e. identity) and extrinsic(i.e. pose) geometry, is a prominent task for generative models of non-Euclidean data such as 3D deformable models. It provides greater interpretability of the latent space, and leads to more control in generation. This work introduces a mesh feature, the conformal factor and normal feature (CFAN),for use in mesh convolutional autoencoders. We further propose CFAN-VAE, a novel architecture that disentangles identity and pose using the CFAN feature. Requiring no label information on the identity or pose during training, CFAN-VAE achieves geometric disentanglement in an unsupervisedway. Our comprehensive experiments, including reconstruction, interpolation, generation, and identity/pose transfer, demonstrate CFAN-VAE achieves state-of-the-art performance on unsupervised geometric disentanglement. We also successfully detect a level of geometric disentanglement in mesh convolutional autoencoders that encode xyz-coordinates directly by registering its latent space to that of CFAN-VAE.

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。

↑