<div dir="ltr">Hi all,<div><br></div><div>Just a reminder that my defense is tomorrow afternoon. Please come by if you are free -- I have ordered some nice cheeses and meats for you to snack on :)</div><div><br></div><div>Chris</div><div><br></div><div><br><div class="gmail_quote"><div dir="ltr">---------- Forwarded message ---------<br>From: Jillian Title <<a href="mailto:jillian.title@cs.ucsb.edu">jillian.title@cs.ucsb.edu</a>><br>Date: Thu, Jan 14, 2016 at 2:06 PM<br>Subject: [grads] PhD Defense - Christopher Sweeney - Friday 1/22/16<br>To: <<a href="mailto:grads@cs.ucsb.edu">grads@cs.ucsb.edu</a>>, <<a href="mailto:faculty@cs.ucsb.edu">faculty@cs.ucsb.edu</a>>, <<a href="mailto:lecturers@cs.ucsb.edu">lecturers@cs.ucsb.edu</a>>, <<a href="mailto:research@lists.cs.ucsb.edu">research@lists.cs.ucsb.edu</a>>, <<a href="mailto:colloquium@lists.connect.ucsb.edu">colloquium@lists.connect.ucsb.edu</a>><br></div><br><br>
<div bgcolor="#FFFFFF" text="#000000">
PhD Defense<br>
<b>Christopher Sweeney</b><br>
Friday, January 22nd at 2pm<br>
HFH 1132<br>
<b><br>
</b><b>Committee: </b>Tobias Höllerer (Co-Chair), Matthew Turk
(Co-Chair), Pradeep Sen, Noah Snavely<br>
<br>
<b>Title:</b> Modeling and Calibrating the Distributed Camera<br>
<br>
<b>Abstract: </b><br>
<br>
Structure-from-Motion (SfM) is a powerful tool for computing 3D
reconstructions from images of a scene and has wide applications in
computer vision, scene recognition, and augmented and virtual
reality. Standard SfM pipelines make strict assumptions about the
capturing devices in order to simplify the process for estimating
camera geometry and 3D structure. Specifically, most methods require
monocular cameras with known focal length calibration. When
considering large-scale SfM from internet photo collections, EXIF
calibrations cannot used reliably. Further, the requirement of
single camera systems limits the scalability of SfM. <br>
<br>
This thesis proposes to remove these constraints by instead
considering the collection of cameras as a "distributed camera" that
encapsulates the image and geometric information of all cameras
simultaneously. First, I provide full generalizations to the
relative camera pose and absolute camera pose problems. These
generalizations are more expressive and extend the traditional
single-camera problems to distributed cameras, forming the basis for
a novel hierarchical SfM pipeline that exhibits state-of-the-art
performance on large-scale datasets. Second, I describe two
efficient methods for estimating camera focal lengths for the
distributed camera when calibration is not available. Finally, I
show how removing these constraints enables a simpler, more scalable
SFM pipeline that is capable of handling uncalibrated cameras at
scale.<br>
<br>
Everyone Welcome!<br>
<br>
<pre cols="72">--
Jillian Title
Graduate Advisor
Department of Computer Science
University of California Santa Barbara
Harold Frank Hall 2104
Santa Barbara, CA 93106-5110
(805) 893-4322</pre>
</div>
_______________________________________________<br>
grads maillist - <a href="mailto:grads@lists.cs.ucsb.edu" target="_blank">grads@lists.cs.ucsb.edu</a><br>
<a href="https://lists.cs.ucsb.edu/mailman/listinfo/grads" rel="noreferrer" target="_blank">https://lists.cs.ucsb.edu/mailman/listinfo/grads</a><br>
</div></div></div>