Pointflow: 3D point cloud generation with continuous normalizing flows
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Pointflow : 3D point cloud generation with continuous normalizing flows. / Yang, Guandao; Huang, Xun; Hao, Zekun; Liu, Ming Yu; Belongie, Serge; Hariharan, Bharath.
In: Proceedings of the IEEE International Conference on Computer Vision, 10.2019, p. 4540-4549.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Pointflow
T2 - 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
AU - Yang, Guandao
AU - Huang, Xun
AU - Hao, Zekun
AU - Liu, Ming Yu
AU - Belongie, Serge
AU - Hariharan, Bharath
N1 - Funding Information: This work was supported in part by a research gift from Magic Leap. Xun Huang was supported by NVIDIA Graduate Fellowship. Publisher Copyright: © 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape. This formulation allows us to both sample shapes and sample an arbitrary number of points from a shape. Our generative model, named PointFlow, learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Empirically, we demonstrate that PointFlow achieves state-of-the-art performance in point cloud generation. We additionally show that our model can faithfully reconstruct point clouds and learn useful representations in an unsupervised manner. The code is available at https://github.com/stevenygd/PointFlow.
AB - As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape. This formulation allows us to both sample shapes and sample an arbitrary number of points from a shape. Our generative model, named PointFlow, learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Empirically, we demonstrate that PointFlow achieves state-of-the-art performance in point cloud generation. We additionally show that our model can faithfully reconstruct point clouds and learn useful representations in an unsupervised manner. The code is available at https://github.com/stevenygd/PointFlow.
UR - http://www.scopus.com/inward/record.url?scp=85081931570&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2019.00464
DO - 10.1109/ICCV.2019.00464
M3 - Conference article
AN - SCOPUS:85081931570
SP - 4540
EP - 4549
JO - Proceedings of the IEEE International Conference on Computer Vision
JF - Proceedings of the IEEE International Conference on Computer Vision
SN - 1550-5499
Y2 - 27 October 2019 through 2 November 2019
ER -
ID: 301823903