TY - GEN
T1 - VoronoiNet
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
AU - Williams, Francis
AU - Parent-Levesque, Jerome
AU - Nowrouzezahrai, Derek
AU - Panozzo, Daniele
AU - Yi, Kwang Moo
AU - Tagliasacchi, Andrea
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/6
Y1 - 2020/6
N2 - Voronoi diagrams are highly compact representations that are used in various Graphics applications. In this work, we show how to embed a differentiable version of it - via a novel deep architecture - into a generative deep network. By doing so, we achieve a highly compact latent embedding that is able to provide much more detailed reconstructions, both in 2D and 3D, for various shapes. In this tech report, we introduce our representation and present a set of preliminary results comparing it with recently proposed implicit occupancy networks.
AB - Voronoi diagrams are highly compact representations that are used in various Graphics applications. In this work, we show how to embed a differentiable version of it - via a novel deep architecture - into a generative deep network. By doing so, we achieve a highly compact latent embedding that is able to provide much more detailed reconstructions, both in 2D and 3D, for various shapes. In this tech report, we introduce our representation and present a set of preliminary results comparing it with recently proposed implicit occupancy networks.
UR - http://www.scopus.com/inward/record.url?scp=85090152582&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090152582&partnerID=8YFLogxK
U2 - 10.1109/CVPRW50498.2020.00140
DO - 10.1109/CVPRW50498.2020.00140
M3 - Conference contribution
AN - SCOPUS:85090152582
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1069
EP - 1073
BT - Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PB - IEEE Computer Society
Y2 - 14 June 2020 through 19 June 2020
ER -