VisualSFM : A Visual Structure from Motion System
VisualSFM is a GUI application for 3D reconstruction using structure from motion (SFM). The reconstruction system integrates several of my previous projects: SIFT on GPU(SiftGPU), Multicore Bundle Adjustment, and Towards Linear-time Incremental Structure from Motion. In particular, both the GUI SfM system and SiftGPU started as course projects when I was at UNC. VisualSFM runs very fast by exploiting multicore parallelism in feature detection, feature matching, and bundle adjustment.
In addition, VisualSFM provides the interfaces to run Yasutaka Furukawa's PMVS/CMVS tool and to prepare data for Michal Jancosek's CMP-MVS. This software also comes with two UNC research projects: Schematic Surface Reconstruction and Single View Repetition Analysis.
Reconstruct 3D models by a few button clicks, and you can
watch the dynamic reconstruction process!
You still have the option to run from command line without a GUI!
Download V0.5.22 (perspective view, VLfeat support, Possible translation, ... changelog)
Windows (x64, win32, install instructions)
Linux (x86_64, i386, install instructions)
Mac OSX (x86_64, i386, install instructions, check out the package contributed by Iván)
*
Post questions and see discussions at our
Google Group, or email
me with VisualSFM in the title.
* VisualSFM is free for personal, non-profit or academic use.
Check README for more details.
* Please cite the tool and related
publications according to
README
The changelist page offers limited documentations for recently added features.
Introductory videos(1, 2) and a tutorial by Eugene Liscio. Tutorial in French by Mathis Fantin.
Below is a 3 minute live run of reconstruction of 130
images(using pre-computed matches).