diff --git a/docs/assets/Bibtex.txt b/docs/assets/Bibtex.txt new file mode 100644 index 0000000..ab79166 --- /dev/null +++ b/docs/assets/Bibtex.txt @@ -0,0 +1,6 @@ +@article{TODO, + title={PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows}, + author={TODO}, + journal={TODO}, + year={2019} +} \ No newline at end of file diff --git a/docs/assets/arch_bw.jpg b/docs/assets/arch_bw.jpg new file mode 100644 index 0000000..cf0ba2f Binary files /dev/null and b/docs/assets/arch_bw.jpg differ diff --git a/docs/assets/flows.gif b/docs/assets/flows.gif new file mode 100644 index 0000000..dabf7b0 Binary files /dev/null and b/docs/assets/flows.gif differ diff --git a/docs/assets/paper.jpg b/docs/assets/paper.jpg new file mode 100644 index 0000000..ad2aff5 Binary files /dev/null and b/docs/assets/paper.jpg differ diff --git a/docs/assets/teaser.gif b/docs/assets/teaser.gif new file mode 100644 index 0000000..b99214e Binary files /dev/null and b/docs/assets/teaser.gif differ diff --git a/docs/index.html b/docs/index.html new file mode 100755 index 0000000..e19fde6 --- /dev/null +++ b/docs/index.html @@ -0,0 +1,183 @@ + + + + + + + + + + PointFlow + + + + +
+
+
+

PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

+
+
+ +
+ Guandao Yang* + Xun Huang* + Zekun Hao + Ming-Yu Liu + Serge Belongie + Bharath Hariharan +
+ +
+
+

+ Cornell University + Cornell Tech + NVIDIA +

+
+
+ +
+ airplane +
+
+ + +
+
+
+
+ +
+ + paper-snapshot + +
+
+
+ + [Arxiv] + + + [Codes] + + + [Bibtex] + +
+
+
+
+

Abstract

+

+ 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 + computation of the likelihood during training and allows us + to train our model in the variational inference framework. + Empirically, we demonstrate that PointFlow achieves stateof- + 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. +

+
+ +
+
+ + +
+
+ +
+
+

Video

+
+
+ + +
+
+ +
+
+ +
+ + + + +
+
+
+
+

Architecture

+
+
+ + +
+
+ architecture +
+
+
+ + +
+
+
+
+

Flow Transformation

+
+
+
+
+ flow-airplane-4 +
+
+
+ + +
+
+ +
+
+

Acknowledgements

+

This work was supported in part by a research gift from Magic Leap. Xun Huang was supported by NVIDIA fellowship.

+
+
+
+ + + + + + + +