<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=windows-1252">
</head>
<body bgcolor="#FFFFFF" text="#000000">
Good stuff from Chao on display tomorrow.<br>
Every Autonian is welcome to join and listen to his talk.<br>
<br>
Artur<br>
<div class="moz-forward-container"><br>
<br>
-------- Forwarded Message --------
<table class="moz-email-headers-table" border="0" cellpadding="0"
cellspacing="0">
<tbody>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">Subject:
</th>
<td>PhD Speaking Qualifier (3-4pm, Mon, May 8th) - NSH 1109
- Matting and Depth Recovery of Thin Structures using a
Focal Stack</td>
</tr>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">Date: </th>
<td>Fri, 05 May 2017 10:37:59 -0400</td>
</tr>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">From: </th>
<td>Chao Liu <a class="moz-txt-link-rfc2396E" href="mailto:chao.liu@cs.cmu.edu"><chao.liu@cs.cmu.edu></a></td>
</tr>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">Reply-To:
</th>
<td><a class="moz-txt-link-abbreviated" href="mailto:chao.liu@cs.cmu.edu">chao.liu@cs.cmu.edu</a></td>
</tr>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">To: </th>
<td><a class="moz-txt-link-abbreviated" href="mailto:ri-people@cs.cmu.edu">ri-people@cs.cmu.edu</a></td>
</tr>
</tbody>
</table>
<br>
<br>
<pre>Hi everyone,
I will be talking about my work on depth recovery for fine-grained
structures for the PhD speaking qualifier next Monday (May 8th) at
3:00pm at NSH 1109. Everyone is invited.
-----------------
Time:
May 8, 2017, 3:00PM - 4:00PM
Location:
NSH 1109
Title:
Matting and Depth Recovery of Thin Structures using a Focal Stack
Abstract:
Thin structures such as fences, grass and vessels are common in
photography and scientific imaging. They exhibit complex 3D structures
with sharp depth variations/discontinuities and mutual occlusions. In
this paper, we develop a method to estimate the occlusion matte and
depths of thin structures from a focal image stack, which is obtained
either by varying the focus/aperture of the lens or computed from a
one-shot light field image.
We propose an image formation model that explicitly describes the
spatially varying optical blur and mutual occlusions for structures
located at different depths. Based on the model, we derive an efficient
MCMC inference algorithm that enables direct and analytical computations
of the iterative update for the model/images without re-rendering images
in the sampling process. Then, the depths of the thin structures are
recovered using gradient descent with the differential terms computed
using the image formation model.
We apply the proposed method to scenes at both macro and micro scales.
For macro-scale, we evaluate our method on scenes with complex 3D thin
structures such as tree branches and grass. For micro-scale, we apply
our method to in-vivo microscopic images of micro-vessels with diameters
less than 50 um. To our knowledge, the proposed method is the first
approach to reconstruct the 3D structures of micro-vessels from
non-invasive in-vivo image measurements.
Committee:
Srinivasa Narasimhan (co-advisor)
Artur Dubrawski (co-advisor)
Aswin Sankaranarayanan
Yuxiong Wang
-----------------
Thank you!
- Chao
</pre>
</div>
</body>
</html>