TY - GEN
T1 - Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation
AU - Rakotosaona, Marie Julie
AU - Ovsjanikov, Maks
N1 - KAUST Repository Item: Exported on 2021-06-30
Acknowledged KAUST grant number(s): CRG-2017-3426
Acknowledgements: Parts of this work were supported by the KAUST CRG-2017-3426 Award and the ERC Starting Grant No. 758800 (EXPROTEA).
This publication acknowledges KAUST support, but has no KAUST affiliated authors.
PY - 2020/11/3
Y1 - 2020/11/3
N2 - We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape information, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across different datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines. Both the code and our pre-trained network can be found online: https://github.com/mrakotosaon/intrinsic_interpolations.
AB - We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape information, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across different datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines. Both the code and our pre-trained network can be found online: https://github.com/mrakotosaon/intrinsic_interpolations.
UR - http://hdl.handle.net/10754/669821
UR - https://link.springer.com/10.1007/978-3-030-58536-5_39
UR - http://www.scopus.com/inward/record.url?scp=85097222579&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-58536-5_39
DO - 10.1007/978-3-030-58536-5_39
M3 - Conference contribution
SN - 9783030585358
SP - 655
EP - 672
BT - Computer Vision – ECCV 2020
PB - Springer International Publishing
ER -