What 3D scene reconstruction methods does the term "multi-view stereo" encompass? Is it only used for methods that apply binocular stereo algorithms (taking 2 views as input) in a pairwise manner? Or only methods based on disparity estimation? If not why is the term "stereo" used?
$\begingroup$ $\endgroup$
2 
- 2$\begingroup$ Where have you seen that term? Stereo 3D reconstruction is a special case of multi-view reconstruction as far as I know. I have never seen the term "multi-view stereo". $\endgroup$Dragonseel– Dragonseel2016-02-11 14:23:38 +00:00Commented Feb 11, 2016 at 14:23
- 2$\begingroup$ For example dl.acm.org/citation.cfm?id=1153518 $\endgroup$tmlen– tmlen2016-02-11 14:31:27 +00:00Commented Feb 11, 2016 at 14:31
Add a comment |
1 Answer
$\begingroup$ $\endgroup$
Multi-view stereo (MVS) is the general term given to a group of techniques that use stereo correspondence as their main cue and use more than two images.
A quote from 'Multi-View Stereo: A Tutorial' by Yasutaka Furukawa and Carlos Hernández.
So to paraphrase: We have a set of images that is larger than two, and use them in a pairwise manner by applying techniques that finde stereo correspondences to reconstruct the object shown in them.
If you want to know more about MVS algorithms that paper I linked seems to be pretty good and at least Furukawa is a name that I know and have read papers from, so he seems to know the topic.
