Safran/PointFlow
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Update

Browse source
This commit is contained in:
Grendel Yang 2019-06-30 01:17:32 -07:00
parent 90037779a2
commit 9c17c960f3
1 changed files with 14 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
docs/index.html
View file

@ -22,12 +22,12 @@
<!-- authors --> <!-- authors -->
<div class='row text-center h5 font-weight-bold pl-4 pr-4 mb-4'> <div class='row text-center h5 font-weight-bold pl-4 pr-4 mb-4'>
<a class="col-3" href="http://www.guandaoyang.com"><span>Guandao Yang*</span></a> <a class="col-md-3 col-xs-6" href="http://www.guandaoyang.com"><span>Guandao Yang*</span></a>
<a class="col-3" href="http://www.cs.cornell.edu/~xhuang/"><span>Xun Huang*</span></a> <a class="col-md-3 col-xs-6" href="http://www.cs.cornell.edu/~xhuang/"><span>Xun Huang*</span></a>
<a class="col-3" href="http://www.cs.cornell.edu/~zekun/"><span>Zekun Hao</span></a> <a class="col-md-3 col-xs-6" href="http://www.cs.cornell.edu/~zekun/"><span>Zekun Hao</span></a>
<a class="col-3" href="http://mingyuliu.net/"><span>Ming-Yu Liu</span></a> <a class="col-md-3 col-xs-6" href="http://mingyuliu.net/"><span>Ming-Yu Liu</span></a>
<a class="col-6" href="http://blogs.cornell.edu/techfaculty/serge-belongie/"><span>Serge Belongie</span></a> <a class="col-md-6 col-xs-6" href="http://blogs.cornell.edu/techfaculty/serge-belongie/"><span>Serge Belongie</span></a>
<a class="col-6" href="http://home.bharathh.info/"><span>Bharath Hariharan</span></a> <a class="col-md-6 col-xs-6" href="http://home.bharathh.info/"><span>Bharath Hariharan</span></a>
</div> </div>
<!-- affiliations --> <!-- affiliations -->
@ -50,9 +50,9 @@
<div> <div>
<hr> <hr>
<div class='row'> <div class='row'>
<div class='col-3 text-center col-sm-3'> <div class='col-md-3 col-sm-3 col-xs-12 text-center col-sm-3'>
<div class="row mt-4"> <div class="row mt-4">
<a href="assets/PointFlow.pdf"> <a href="assets/PointFlow.pdf" style="max-width:200px; margin-left:auto; margin-right:auto">
<img src="assets/paper.jpg" alt="paper-snapshot" class="img-thumbnail" width="80%" style="box-shadow: 10px 10px 5px grey;"> <img src="assets/paper.jpg" alt="paper-snapshot" class="img-thumbnail" width="80%" style="box-shadow: 10px 10px 5px grey;">
</a> </a>
</div> </div>
@ -70,8 +70,8 @@
</div> </div>
</div> </div>
</div> </div>
<div class='col-9'> <div class='col-md-9 col-sm-9 col-xs-12'>
<p class='h4 font-weight-bold'>Abstract</p> <p class='h4 font-weight-bold '>Abstract</p>
<p style='line-height:1;'> <p style='line-height:1;'>
As 3D point clouds become the representation of choice As 3D point clouds become the representation of choice
for multiple vision and graphics applications, the ability to for multiple vision and graphics applications, the ability to
@ -127,7 +127,6 @@
</div> </div>
<!-- Architecture, explaination --> <!-- Architecture, explaination -->
<div> <div>
<hr> <hr>
@ -138,10 +137,10 @@
</div> </div>
<div class='row mt-3'> <div class='row mt-3'>
<div class='col-7 mt-3'> <div class='col-md-7 col-sm-7 col-xs-12 mt-3'>
<img src="assets/pcl_is_a_sample.gif" class="img-fluid" alt="architecture"> <img src="assets/pcl_is_a_sample.gif" class="img-fluid" alt="architecture">
</div> </div>
<div class='col-5 align-middle mt-5'> <div class='col-md-5 col-sm-5 col-xs-12 align-middle mt-5'>
<p class="text-break"> <p class="text-break">
Each shape can be viewed as a distribution of 3D points. 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. In such distribution, points on the shape have higher probability and are more likely to be sampled.
@ -151,14 +150,14 @@
</div> </div>
<div class='row mt-3'> <div class='row mt-3'>
<div class='col-5 align-middle mt-5'> <div class='col-md-5 col-sm-5 col-xs-12 align-middle mt-5'>
<p class="text-break"> <p class="text-break">
We use two continuous normalizing flows (CNF) to model the distribution of shapes, each of which is a distribution of 3D points. 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 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. The point CNF transforms 3D points sampled from the point prior to a point cloud on the shape.
</p> </p>
</div> </div>
<div class='col-7 mt-3'> <div class='col-md-7 col-sm-7 col-xs-12 mt-3'>
<img src="assets/inference-architecture.gif" class="img-fluid" alt="architecture"> <img src="assets/inference-architecture.gif" class="img-fluid" alt="architecture">
</div> </div>
</div> </div>