<?xml version="1.0" encoding="UTF-8"?><!-- generator="wordpress/1.5.1-alpha" -->
<rss version="2.0" 
	xmlns:content="http://purl.org/rss/1.0/modules/content/">
<channel>
	<title>Comments on: I don&#8217;t think the baby&#8217;s face is that important</title>
	<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/</link>
	<description>the blog that is not dansdata.com</description>
	<pubDate>Thu, 28 Aug 2008 19:44:42 +0000</pubDate>
	<generator>http://wordpress.org/?v=1.5.1-alpha</generator>

	<item>
		<title>by: dvayn</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1297</link>
		<pubDate>Sat, 25 Aug 2007 00:12:58 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1297</guid>
					<description>Indeed. Surprisingly enough I actually went through most of the paper when you posted it earlier.</description>
		<content:encoded><![CDATA[	<p>Indeed. Surprisingly enough I actually went through most of the paper when you posted it earlier.
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Daniel Rutter</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1296</link>
		<pubDate>Fri, 24 Aug 2007 20:47:14 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1296</guid>
					<description>&lt;i&gt;Many of the fancy and impressive algorithms that seem to do EVERYTHING, really just do it well for the select choice of scenes&lt;/i&gt;

The Hayes/Efros scene completion technique also fails badly in certain situations; their &lt;a href=&quot;http://graphics.cs.cmu.edu/projects/scene-completion/scene-completion.pdf&quot; rel=&quot;nofollow&quot;&gt;PDF&lt;/a&gt; has several such cases.</description>
		<content:encoded><![CDATA[	<p><i>Many of the fancy and impressive algorithms that seem to do EVERYTHING, really just do it well for the select choice of scenes</i></p>
	<p>The Hayes/Efros scene completion technique also fails badly in certain situations; their <a href="http://graphics.cs.cmu.edu/projects/scene-completion/scene-completion.pdf" rel="nofollow">PDF</a> has several such cases.
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: dvayn</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1295</link>
		<pubDate>Fri, 24 Aug 2007 13:38:16 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1295</guid>
					<description>Certainly an interesting and subtly clever application of gradient information! Interesting, but the fact that it's not completely automatic in terms of it recognizing psychologically important areas of the image is a little dose of reality for those impressed by today's computer vision research projects. Many of the fancy and impressive algorithms that seem to do EVERYTHING, really just do it well for the select choice of scenes that were made for the demonstration. After all, with a digital projector and a digital camera, you too can make a fully automatic 3-D scanner (given the right scene, of course):

http://cs.bc.edu/research/bachelors_theses/2006

Check the last thesis - tooting my own horn a little, but I thought it would go along with Dan's image research trend :) </description>
		<content:encoded><![CDATA[	<p>Certainly an interesting and subtly clever application of gradient information! Interesting, but the fact that it&#8217;s not completely automatic in terms of it recognizing psychologically important areas of the image is a little dose of reality for those impressed by today&#8217;s computer vision research projects. Many of the fancy and impressive algorithms that seem to do EVERYTHING, really just do it well for the select choice of scenes that were made for the demonstration. After all, with a digital projector and a digital camera, you too can make a fully automatic 3-D scanner (given the right scene, of course):</p>
	<p><a href='http://cs.bc.edu/research/bachelors_theses/2006' rel='nofollow'>http://cs.bc.edu/research/bachelors_theses/2006</a></p>
	<p>Check the last thesis - tooting my own horn a little, but I thought it would go along with Dan&#8217;s image research trend :)
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: magetoo</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1292</link>
		<pubDate>Thu, 23 Aug 2007 23:48:29 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1292</guid>
					<description>Thank you, Coral Cache, for the &lt;a href=&quot;http://www.faculty.idc.ac.il.nyud.net/arik/IMRet-All.mov&quot; rel=&quot;nofollow&quot;&gt;mov version&lt;/a&gt;.</description>
		<content:encoded><![CDATA[	<p>Thank you, Coral Cache, for the <a href="http://www.faculty.idc.ac.il.nyud.net/arik/IMRet-All.mov" rel="nofollow">mov version</a>.
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Arlo</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1290</link>
		<pubDate>Thu, 23 Aug 2007 12:54:25 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1290</guid>
					<description>Mind-dropping and jaw-blowing stuff.  Maybe you've already seen it, but there's yet another crazy image research project out there. Check out the Ted Talk on Photosynth:  &lt;a href=&quot;http://www.ted.com/index.php/talks/view/id/129&quot; rel=&quot;nofollow&quot;&gt;Blaise Aguera y Arcas: Jaw-dropping Photosynth demo&lt;/a&gt;</description>
		<content:encoded><![CDATA[	<p>Mind-dropping and jaw-blowing stuff.  Maybe you&#8217;ve already seen it, but there&#8217;s yet another crazy image research project out there. Check out the Ted Talk on Photosynth:  <a href="http://www.ted.com/index.php/talks/view/id/129" rel="nofollow">Blaise Aguera y Arcas: Jaw-dropping Photosynth demo</a>
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Microfrost</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1289</link>
		<pubDate>Thu, 23 Aug 2007 12:51:26 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1289</guid>
					<description>*nerdgasm*</description>
		<content:encoded><![CDATA[	<p>*nerdgasm*
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Stark</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1288</link>
		<pubDate>Thu, 23 Aug 2007 04:47:46 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1288</guid>
					<description>The removal method there made my jaw drop.  Having done this sort of work in Photoshop on more than a few occasions... just wow.  That is amazing.  

Just think... no more vacation snaps with some random person in them!  ;)
</description>
		<content:encoded><![CDATA[	<p>The removal method there made my jaw drop.  Having done this sort of work in Photoshop on more than a few occasions&#8230; just wow.  That is amazing.  </p>
	<p>Just think&#8230; no more vacation snaps with some random person in them!  ;)
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Joachims</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1286</link>
		<pubDate>Thu, 23 Aug 2007 02:19:00 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1286</guid>
					<description>My first thought: Wow, cool technique!
My second thought: Another step away from the idea that images (photos) are representations of observable reality, and toward images as art that only takes inspiration from reality.
My third thought: Wow, now everybody* can be their own &lt;a href=&quot;http://en.wikipedia.org/wiki/Nineteen_Eighty-Four&quot; title=&quot;Ministry Of Truth&quot; rel=&quot;nofollow&quot;&gt;Ministry Of Truth&lt;/a&gt; (or Nazi- or Stalin-) picture forger and add or remove people or objects from pictures. 

* as opposed to: only people who have the time and knowledge and brains to do it.</description>
		<content:encoded><![CDATA[	<p>My first thought: Wow, cool technique!<br />
My second thought: Another step away from the idea that images (photos) are representations of observable reality, and toward images as art that only takes inspiration from reality.<br />
My third thought: Wow, now everybody* can be their own <a href="http://en.wikipedia.org/wiki/Nineteen_Eighty-Four" title="Ministry Of Truth" rel="nofollow">Ministry Of Truth</a> (or Nazi- or Stalin-) picture forger and add or remove people or objects from pictures. </p>
	<p>* as opposed to: only people who have the time and knowledge and brains to do it.
</p>
]]></content:encoded>
				</item>
	<item>
		<title>by: Rask</title>
		<link>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1285</link>
		<pubDate>Thu, 23 Aug 2007 01:53:51 +0100</pubDate>
		<guid>http://dansdata.blogsome.com/2007/08/23/i-dont-think-the-babys-face-is-that-important/#comment-1285</guid>
					<description>Wow, I want this in my next Photoshop!</description>
		<content:encoded><![CDATA[	<p>Wow, I want this in my next Photoshop!
</p>
]]></content:encoded>
				</item>
</channel>
</rss>
