diff --git a/docs/README.md b/docs/README.md deleted file mode 100644 index e340aaa..0000000 --- a/docs/README.md +++ /dev/null @@ -1,3 +0,0 @@ ---- -permalink: /index.html ---- diff --git a/docs/assets/inference-architecture.gif b/docs/assets/inference-architecture.gif new file mode 100644 index 0000000..183b71c Binary files /dev/null and b/docs/assets/inference-architecture.gif differ diff --git a/docs/assets/pcl_is_a_sample.gif b/docs/assets/pcl_is_a_sample.gif new file mode 100644 index 0000000..9092b72 Binary files /dev/null and b/docs/assets/pcl_is_a_sample.gif differ diff --git a/docs/assets/teaser.gif b/docs/assets/teaser.gif index b99214e..87343d5 100644 Binary files a/docs/assets/teaser.gif and b/docs/assets/teaser.gif differ diff --git a/docs/index.html b/docs/index.html index e19fde6..2fb67cd 100755 --- a/docs/index.html +++ b/docs/index.html @@ -32,9 +32,9 @@
@@ -114,11 +114,10 @@Architecture
+Brief Introduction to the Method
+ Each shape can be viewed as a distribution of 3D points. + In such distribution, points on the shape have higher probability and are more likely to be sampled. + A point cloud can be viewed as a set of sampled points from such a distribution. +
+ We use two continuous normalizing flows (CNF) to model the distribution of shapes, each of which is a distribution of 3D points. + The latent CNF transforms a vector sampled from the shape prior to a latent shape vector. + The point CNF transforms 3D points sampled from the point prior to a point cloud on the shape. +
+Flow Transformation
+Visulaization of the Flow