Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Heli Ben-Hamu"'
Publikováno v:
ICCV
Developing deep learning techniques for geometric data is an active and fruitful research area. This paper tackles the problem of sphere-type surface learning by developing a novel surface-to-image representation. Using this representation we are abl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf8a0a7d3c433d6985a93c47175f32f5
http://arxiv.org/abs/1812.10705
http://arxiv.org/abs/1812.10705
Publikováno v:
ICIP
Image segmentation is often considered a deterministic process with a single ground truth. Nevertheless, in practice, and in particular, when medical imaging analysis is considered, the extraction of regions of interest (ROIs) is ill-posed and the co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::556283f65d543b5c41d3918c1ffb9b12
https://doi.org/10.1109/icip.2018.8451505
https://doi.org/10.1109/icip.2018.8451505
Publikováno v:
ACM Transactions on Graphics
This paper introduces a 3D shape generative model based on deep neural networks. A new image-like ( i.e. , tensor) data representation for genus-zero 3D shapes is devised. It is based on the observation that complicated shapes can be well represented
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c4242626562e2e85e0f5d44fbdb911a