UCLID-Net: Single View Reconstruction in Object Space [article]

Benoit Guillard, Edoardo Remelli, Pascal Fua
2020 arXiv   pre-print
Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve the Euclidean structure of the 3D space objects exist in. In this paper, we show that building a geometry preserving 3-dimensional latent space helps the network concurrently learn global shape regularities and local reasoning in the object coordinate space
more » ... d, as a result, boosts performance. We demonstrate both on ShapeNet synthetic images, which are often used for benchmarking purposes, and on real-world images that our approach outperforms state-of-the-art ones. Furthermore, the single-view pipeline naturally extends to multi-view reconstruction, which we also show.
arXiv:2006.03817v2 fatcat:yxetaoobn5cixh6wctu5xxqhmu