3-D Depth Reconstruction from a Single Still Image (2007) [pdf]

This is some very cool research, though many may be surprised to learn that it is an IJCV journal article from 2007, based on a conference paper from NIPS 2005.<p>Source: <a href="http:&#x2F;&#x2F;www.cs.cornell.edu&#x2F;%7Easaxena&#x2F;learningdepth&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.cs.cornell.edu&#x2F;%7Easaxena&#x2F;learningdepth&#x2F;</a>

As an aside, I really enjoy it when people post articles like this on HN. Technical, but not too niche, and relevant to today&#x27;s interests in technology.

Video is a nice watch, especially as this is from 2007, so the state of the art should be even better. <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=UZ7_ED9g4FY" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=UZ7_ED9g4FY</a>

I wish these groups would make their code available so others could play with it and test it out. Some do, but I wish more did.<p>I would be curious to see the performance of this 3d depth reconstruction technique for non-rigid environments.

Always love seeing computer vision related stuff posted.<p>Incidentally, we have improved on these techniques (given that this came out almost a decade ago!) for scale reconstruction with our mobile monocular SLAM system.<p>The authors are now killing it worldwide (Obviously for Ng) working on applications.

tl:dr; Can combine monocular NN CV techniques with stereo techniques for good, cheap results. AKA: The future of SLAM.