Neural Convolutional Surfaces

Luca Morreale, Noam Aigerman, Paul Guerrero, Vladimir G. Kim, Niloy J. Mitra; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 19333-19342

Abstract

This work is concerned with representation of shapes while disentangling fine, local and possibly repeating geometry, from global, coarse structures. Achieving such disentanglement leads to two unrelated advantages: i) a significant compression in the number of parameters required to represent a given geometry; ii) the ability to manipulate either global geometry, or local details, without harming the other. At the core of our approach lies a novel pipeline and neural architecture, which are optimized to represent one specific atlas, representing one 3D surface. Our pipeline and architecture are designed so that disentanglement of global geometry from local details is accomplished through optimization, in a completely unsupervised manner. We show that this approach achieves better neural shape compression than the state of the art, as well as enabling manipulation and transfer of shape details.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Morreale_2022_CVPR, author = {Morreale, Luca and Aigerman, Noam and Guerrero, Paul and Kim, Vladimir G. and Mitra, Niloy J.}, title = {Neural Convolutional Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {19333-19342} }