Timezone: »

Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
Yi Zhou · Chenglei Wu · Zimo Li · Chen Cao · Yuting Ye · Jason Saragih · Hao Li · Yaser Sheikh

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1291

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.

Author Information

Yi Zhou (University of Southern California)
Chenglei Wu (Facebook)
Zimo Li (University of Southern California)
Chen Cao (Snap Inc.)
Yuting Ye (Facebook Reality Labs)
Jason Saragih (Facebook)
Hao Li (Pinscreen/University of Southern California/USC ICT)
Yaser Sheikh (Facebook Reality Labs)

More from the Same Authors