Comments on: Structure from motion projects http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/ ASTRE Henri experiments with Ogre3D and web stuff Tue, 22 Aug 2017 10:32:15 +0000 hourly 1 http://wordpress.org/?v=3.1.2 By: bryan http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-61809 bryan Mon, 10 Feb 2014 07:10:44 +0000 http://www.visual-experiments.com/?p=1029#comment-61809 i'm interesting with Building Rome on a Cloudless Day but i'm not found source code. Does the source code actually be shared? (sorry for my bad english) i’m interesting with Building Rome on a Cloudless Day but i’m not found source code. Does the source code actually be shared? (sorry for my bad english)

]]> By: admin http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-3265 admin Tue, 05 Apr 2011 09:17:57 +0000 http://www.visual-experiments.com/?p=1029#comment-3265 @marriedwchildren: I'm aware of your product but I didn't see any publication nor downloadable product than I can test with my own dataset: this is why I don't have included it on the list of SFM project I'm interested in. But you seems to have indeed a very accurate SFM solution. I just have one concern about your unbiased comparison: why do you have used so small picture in the PhotoSynth comparison? @marriedwchildren: I’m aware of your product but I didn’t see any publication nor downloadable product than I can test with my own dataset: this is why I don’t have included it on the list of SFM project I’m interested in. But you seems to have indeed a very accurate SFM solution. I just have one concern about your unbiased comparison: why do you have used so small picture in the PhotoSynth comparison?

]]> By: marriedwchildren http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-3241 marriedwchildren Tue, 05 Apr 2011 04:33:34 +0000 http://www.visual-experiments.com/?p=1029#comment-3241 Please take at a look at www.visualsize.com. Visualsize conducted unbiased comparison studies against Bundler, Bundler+PMVS2, and Autodesk Photofly, and demonstrated that their 3D software outperforms all others based on a similar SfM principle by a significant margin. Visualsize provides more than 100 3D models of all kinds of objects using nothing but uncalibrated digital photos. Please take at a look at http://www.visualsize.com. Visualsize conducted unbiased comparison studies against Bundler, Bundler+PMVS2, and Autodesk Photofly, and demonstrated that their 3D software outperforms all others based on a similar SfM principle by a significant margin. Visualsize provides more than 100 3D models of all kinds of objects using nothing but uncalibrated digital photos.

]]> By: admin http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-1836 admin Thu, 23 Dec 2010 10:26:15 +0000 http://www.visual-experiments.com/?p=1029#comment-1836 @Pierre: Thanks! I'm officially on vacation today (no coding allowed during holiday...)! So you'll have to wait 2011 to get the visual studio solution. Hopefully it won't be long! BTW if you try to compile the solution with V3DLIB_ENABLE_LPSOLVE you'll see that LP_solve is needed. Concerning the CycleInference package: I think that <a href="http://people.kyb.tuebingen.mpg.de/jorism/libDAI/" rel="nofollow">libDAI</a> is the only dependency missing (I should be able to compile it myself, but thanks for the help!). @Pierre: Thanks! I’m officially on vacation today (no coding allowed during holiday…)! So you’ll have to wait 2011 to get the visual studio solution. Hopefully it won’t be long! BTW if you try to compile the solution with V3DLIB_ENABLE_LPSOLVE you’ll see that LP_solve is needed. Concerning the CycleInference package: I think that libDAI is the only dependency missing (I should be able to compile it myself, but thanks for the help!).

]]> By: Pierre http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-1833 Pierre Thu, 23 Dec 2010 09:15:33 +0000 http://www.visual-experiments.com/?p=1029#comment-1833 Nice job to make it works ! It seems that the dependency over LP_solve is not used in the code in fact... Just the includes are present ... I'm quite impatient to test it. If you want some help for the cycle inference. Tell me ;) Nice job to make it works !
It seems that the dependency over LP_solve is not used in the code in fact… Just the includes are present …
I’m quite impatient to test it.
If you want some help for the cycle inference. Tell me ;)

]]> By: admin http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-1824 admin Wed, 22 Dec 2010 14:15:52 +0000 http://www.visual-experiments.com/?p=1029#comment-1824 @smoggy: thanks a lot for this link! @Josh Harle: I know that the PhotoSynth/Bundler comparison it's now really fair... But this is the result I got from my <a href="http://photosynth.net/view.aspx?cid=3ed06bd0-8191-4d01-a78e-c0603424764d" rel="nofollow">church dataset</a>. And as I'm using the sparse point cloud for tracking you understand why I'm looking for Bundler alternative. @Pierre: actually I already <a href="http://www.visual-experiments.com/beta/v3d.jpg" rel="nofollow">have it working</a> ;): SfM package: - all binaries are working CycleInference package: - nothing (not tried yet) The windows port wasn't easy due to the number of dependencies (+ some cuda rewrite to be compatible with visual studio): I'll share it once I'll have the scripting complete too. @smoggy: thanks a lot for this link!

@Josh Harle: I know that the PhotoSynth/Bundler comparison it’s now really fair… But this is the result I got from my church dataset. And as I’m using the sparse point cloud for tracking you understand why I’m looking for Bundler alternative.

@Pierre: actually I already have it working ;) :

SfM package:
- all binaries are working

CycleInference package:
- nothing (not tried yet)

The windows port wasn’t easy due to the number of dependencies (+ some cuda rewrite to be compatible with visual studio): I’ll share it once I’ll have the scripting complete too.

]]> By: Pierre http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-1820 Pierre Wed, 22 Dec 2010 13:49:47 +0000 http://www.visual-experiments.com/?p=1029#comment-1820 ETH-V3D Structure-and-Motion software: I’m currently trying to port this to windows, seems to be the most complete Bundler alternative => Will not be easy. Need LP_Solve, Cuda... ETH-V3D Structure-and-Motion software: I’m currently trying to port this to windows, seems to be the most complete Bundler alternative => Will not be easy. Need LP_Solve, Cuda…

]]> By: Josh Harle http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-1815 Josh Harle Wed, 22 Dec 2010 04:58:19 +0000 http://www.visual-experiments.com/?p=1029#comment-1815 Hi Henri, Wow; the PhotoSynth/Bundler comparison is quite an indictment of Bundler results! :) Hi Henri,

Wow; the PhotoSynth/Bundler comparison is quite an indictment of Bundler results! :)

]]> By: smoggy http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-1810 smoggy Tue, 21 Dec 2010 14:42:12 +0000 http://www.visual-experiments.com/?p=1029#comment-1810 include this http://www.ros.org/wiki/ScaViSLAM include this http://www.ros.org/wiki/ScaViSLAM

]]> By: admin http://www.visual-experiments.com/2010/12/20/structure-from-motion-projects/comment-page-1/#comment-1803 admin Tue, 21 Dec 2010 10:14:19 +0000 http://www.visual-experiments.com/?p=1029#comment-1803 @Cesar Lopez: you're right I should have commented all project I'm interested in: <ul> <li>-Building Rome in a Day: just mentioned for reference (using Bundler)</li> <li>-Building Rome on a Cloudless Day: the source code does not contain the sfm solution, but it contains Cuda Ransac and Cuda Gist descriptor with k-medoids and k-nearest neighbors</li> <li>-Samantha: they still don't have released their source code but it sounds very promissing</li> <li>-PhotoSynth: I'm trying to triangulate my own feature tracks using PhotoSynth camera position</li> <li>-ETH-V3D Structure-and-Motion software: I'm currently trying to port this to windows, seems to be the most complete Bundler alternative</li> <li>-Simple Sparse Bundle Adjustment: this is not really a sfm solution, it only does the bundle adjustment but I may use this with OpenSynther</li> <li>-A multi-stage linear approach to structure from motion: this is a very great paper achieving impressive speed-up compared to Bundler and is "drift-free"</li> </ul> So there is not only one alternative to Bundler this is why I'm interested in all this great projects. @Cesar Lopez: you’re right I should have commented all project I’m interested in:

  • -Building Rome in a Day: just mentioned for reference (using Bundler)
  • -Building Rome on a Cloudless Day: the source code does not contain the sfm solution, but it contains Cuda Ransac and Cuda Gist descriptor with k-medoids and k-nearest neighbors
  • -Samantha: they still don’t have released their source code but it sounds very promissing
  • -PhotoSynth: I’m trying to triangulate my own feature tracks using PhotoSynth camera position
  • -ETH-V3D Structure-and-Motion software: I’m currently trying to port this to windows, seems to be the most complete Bundler alternative
  • -Simple Sparse Bundle Adjustment: this is not really a sfm solution, it only does the bundle adjustment but I may use this with OpenSynther
  • -A multi-stage linear approach to structure from motion: this is a very great paper achieving impressive speed-up compared to Bundler and is “drift-free”

So there is not only one alternative to Bundler this is why I’m interested in all this great projects.

]]>