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. VisualSFM runs fast by exploiting multicore parallelism for feature detection, feature matching, and bundle adjustment.
For dense reconstruction, this program supports Yasutaka Furukawa's PMVS/CMVS tool chain, and can prepare data for Michal Jancosek's CMP-MVS. In addition, the output of VisualSFM is natively supported by Mathias Rothermel and Konrad Wenzel's SURE.
|Structure from Motion - A Visual Approach|
Reconstruct 3D with a few button clicks, and
watch the dynamic reconstruction process!
*for nVidia CUDA or CUDA
Windows (x64, win32, install instructions)
Linux (x86_64, i386, install instructions), see the tutorials for Ubuntu or Fedora.
Mac OSX (x86_64, i386, install instructions), see the installers by Dan Monaghan or by Iván.
Post questions and see discussions at the
Google Group, or email me with VisualSFM in the title.
Basic usage, image size, customized matching, controls, parameters, nvm file, demo, ...
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.
|Live Reconstruction Visualization! (more videos)|
Below is a 3 minute live run of reconstruction of 130
images(using pre-computed matches).