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 integrates the execution of Yasutaka Furukawa's PMVS/CMVS tool chain. The SfM output of VisualSFM works with several additional tools, including CMP-MVS by Michal Jancosek, MVE by Michael Goesele's research group, SURE by Mathias Rothermel and Konrad Wenzel, andMeshRecon by Zhuoliang Kang.
Structure from Motion - A Visual InterfaceReconstruct 3D with a few button clicks, and watch the dynamic reconstruction process!
You still have the option to run from command line without a GUI!
Download V0.5.26 (changelog with new feature documentation)
Windows * ( 64-bit, 32-bit, installation guide), *for nVidia CUDA or CUDA Simulation.Windows ( 64-bit, 32-bit, installation guide)
Linux ( 64-bit, 32-bit, installation guide), see the tutorials for Ubuntu or Fedora.
Mac OSX ( 64-bit, 32-bit, installation guide), see the installer by Dan Monaghan.
* VisualSFM is free for personal, non-profit or academic use. See README for more details.
* Please cite VisualSFM according to README in your publication.
Introductory videos( 1, 2) and tutorial by Eugene Liscio. French Tutorial by Mathis Fantin.
*The changelist page offers limited documentations for recently added features.
*Post questions and see discussions & tutorials at the Google Group , or email me privately.
Live Reconstruction Visualization! ( more videos)
Below is a 3 minute live run of reconstruction of 130 images(using pre-computed matches).
width="1008" height="590" src="http://www.youtube.com/embed/5ceiOd8Yx3g" frameborder="0" allowfullscreen="">
from: http://ccwu.me/vsfm/
VisualSFM是一款利用运动结构(SFM)进行3D重建的图形用户界面应用。该系统集成了多个项目,如SIFT on GPU、多核束调整等,通过多核并行处理加速特征检测、匹配及束调整过程。此外,它还整合了Yasutaka Furukawa的PMVS/CMVS工具链以实现更密集的重建。

5355

被折叠的 条评论
为什么被折叠?



