<div dir="ltr">To summarize the paper: they perform SLAM using images directly without any features. They do this by performing an optimization that aligns images in areas of high gradient intensity. Depth estimates at these locations are optimized and the uncertainty is recorded. Then they optimize keyframes to include scale in addition to rotation and translation, so they're more robust to drift. Any frames that aren't keyframes are used to reduce the variance in depth estimation.<div><br></div><div>There were largely mixed opinions of this paper at ECCV and many were not that impressed. I attended the talk and had a long discussion with Jakob afterwards as well. Overall, the results are undeniably awesome and I'm excited that it is open source but I don't think it is revolutionary by any means. I would argue only has a tiny novelty. This is almost exactly the same work that the Sarnoff Group (Michal Irani, David Nister, Anandan, etc.) was doing in the 90's... but now we have faster computers. The only addition I can see is tracking scale in keyframes which allows you to easily change environments (i.e. go from indoor to outdoor) without scale drift.</div><div><div><br></div><div>However, I would say that people should definitely start using this over PTAM assuming the source code that is released is reasonable. It performs faster, gives more accurate depth maps, and does not require multiple threads so there is almost no reason to not use it...</div><div><br></div></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Thu, Sep 11, 2014 at 9:52 AM, Tobias Hollerer <span dir="ltr"><<a href="mailto:holl@cs.ucsb.edu" target="_blank">holl@cs.ucsb.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><br>
People in the AR tracking community I respect and trust speak highly of (or rather have high expectation for) this work<br>
that is being presented at ECCV:<br>
<br>
<a href="http://vision.in.tum.de/research/lsdslam" target="_blank">http://vision.in.tum.de/<u></u>research/lsdslam</a><br>
Open source license to be announced imminently.<br>
<br>
Chris, would you try to catch the talk at ECCV (today?), and report your impressions to the lab?<br>
Thanks & Cheers,<br>
<br>
Tobias<span class="HOEnZb"><font color="#888888"><br>
<br>
-- <br>
Tobias Hollerer<br>
Professor, Department of Computer Science<br>
University of California, Santa Barbara, CA 93106-5110<br>
<br>
<a href="mailto:holl@cs.ucsb.edu" target="_blank">holl@cs.ucsb.edu</a>, Office: <a href="tel:%28805%29284-9395" value="+18052849395" target="_blank">(805)284-9395</a>, Fax: <a href="tel:%28805%29893-8553" value="+18058938553" target="_blank">(805)893-8553</a><br>
<br>
</font></span><br>_______________________________________________<br>
Ilab-users mailing list<br>
<a href="mailto:Ilab-users@lists.cs.ucsb.edu">Ilab-users@lists.cs.ucsb.edu</a><br>
<a href="https://lists.cs.ucsb.edu/mailman/listinfo/ilab-users" target="_blank">https://lists.cs.ucsb.edu/mailman/listinfo/ilab-users</a><br></blockquote></div><br></div>