MongeNet: Efficient Sampler for Geometric Deep Learning

Leo Lebrat, Rodrigo Santa Cruz, Clinton Fookes, Olivier Salvado; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 16664-16673

Abstract


Recent advances in geometric deep-learning introduce complex computational challenges for evaluating the distance between meshes. From a mesh model, point clouds are necessary along with a robust distance metric to assess surface quality or as part of the loss function for training models. Current methods often rely on a uniform random mesh discretization, which yields irregular sampling and noisy distance estimation. In this paper we introduce MongeNet, a fast and optimal transport based sampler that allows for an accurate discretization of a mesh with better approximation properties. We compare our method to the ubiquitous random uniform sampling and show that the approximation error is almost half with a very small computational overhead.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Lebrat_2021_CVPR, author = {Lebrat, Leo and Cruz, Rodrigo Santa and Fookes, Clinton and Salvado, Olivier}, title = {MongeNet: Efficient Sampler for Geometric Deep Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {16664-16673} }