COLMAP 是一个通用的 Structure-from-Motion (SfM) 和 Multi-View Stereo (MVS) pipeline,具有图形和命令行界面。它提供了丰富的功能,可用于重建有序和无序图像集。
![]()
![]()
如果你将此项目用于您的研究,请引用:
@inproceedings{schoenberger2016sfm,
author={Sch\"{o}nberger, Johannes Lutz and Frahm, Jan-Michael},
title={Structure-from-Motion Revisited},
booktitle={Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2016},
}
@inproceedings{schoenberger2016mvs,
author={Sch\"{o}nberger, Johannes Lutz and Zheng, Enliang and Pollefeys, Marc and Frahm, Jan-Michael},
title={Pixelwise View Selection for Unstructured Multi-View Stereo},
booktitle={European Conference on Computer Vision (ECCV)},
year={2016},
}
如果你使用 image retrieval / vocabulary tree engine,请同时引用:
@inproceedings{schoenberger2016vote,
author={Sch\"{o}nberger, Johannes Lutz and Price, True and Sattler, Torsten and Frahm, Jan-Michael and Pollefeys, Marc},
title={A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval},
booktitle={Asian Conference on Computer Vision (ACCV)},
year={2016},
}
COLMAP 建立在现有成果之上,在 COLMAP 中使用特定算法时,请注明原始作者(如源代码中所述),并考虑引用相关的第三方依赖项(例如 ceres-solver、poselib、sift-gpu 和 vlfeat)。