一·背景

在历经多日困顿，迷茫与自我怀疑且在图书馆查找资料无果之后，今晚无意在网上找到CMVS程序，可以采用Python进行二次开发，曙光出现！

二·CMVS——Clustering Views for Multi-view Stereo (CMVS)

2.1 介绍

Many multi-view stereo (MVS) algorithms do not scale well to a large number of input images (lack of computational and memory resources). This software (CMVS) takes the output of a structure-from-motion (SfM) software as input, then decomposes the input images into a set of image clusters of managable size. An MVS software can be used to process each cluster independently and in parallel, where the union of reconstructions from all the clusters should not miss any details that can be otherwise obtained from the whole image set. CMVS should be used in conjunction with an SfM software Bundler and an MVS software PMVS2 (PMVS version 2). The software package includes all the source code distributed under GPL.

The software was developped when Yasutaka Furukawa was a postdoc at University of Washington under the supervision of Prof. Brian Curless and Prof. Steve Seitz at University of Washington, and Richard Szeliski at Microsoft Research.

Multi-view stereo software PMVS2, which is included in the CMVS package, was developped when Yasutaka Furukawa was a graduate student at University of Illinois at Urbana-Champaign under the supervision of Prof. Jean Ponce, who was affiliated with University of Illinois at Urbana-Champaign and Ecole Normale Supérieure. Further modifications and enhancements were added when Yasutaka Furukawa was a postdoc at University of Washington.

The software was developped when Yasutaka Furukawa was a postdoc at University of Washington under the supervision of Prof. Brian Curless and Prof. Steve Seitz at University of Washington, and Richard Szeliski at Microsoft Research.

Multi-view stereo software PMVS2, which is included in the CMVS package, was developped when Yasutaka Furukawa was a graduate student at University of Illinois at Urbana-Champaign under the supervision of Prof. Jean Ponce, who was affiliated with University of Illinois at Urbana-Champaign and Ecole Normale Supérieure. Further modifications and enhancements were added when Yasutaka Furukawa was a postdoc at University of Washington.

PMVS2 is used for real production purposes by Industrial Light & Magic, Weta Digital, and Google Inc.PMVS2 is used for real production purposes by Industrial Light & Magic, Weta Digital, and Google Inc.

from https://www.di.ens.fr/cmvs/

许多多视图立体视觉(MVS)算法不能很好地适应大量输入图像(缺乏计算和内存资源)。该软件(CMVS)以SfM (structure-from-motion)软件的输出为输入，然后将输入图像分解为一组大小可管理的图像集群。MVS软件可以用来处理每个集群独立和并行,在重建的联盟所有的区域不应该错过任何细节,可以从整个图像集。否则获得巨细胞病毒应该结合使用SfM软件打包机和MVS PMVS2 (pmv版本2)。软件包包括所有的源代码分发GPL下。

该软件是在华盛顿大学Brian Curless教授和Steve Seitz教授以及微软研究院Richard Szeliski的指导下，古川康孝(Yasutaka Furukawa)在华盛顿大学博士后期间开发的。

多视图立体软件PMVS2包含在CMVS包中，是古川康隆(Yasutaka Furukawa)在伊利诺伊大学香槟分校(University of Illinois at Urbana-Champaign)和巴黎高等师范学院(Ecole Normale Superieure)的Jean Ponce教授指导下开发的。古川康隆是伊利诺伊大学香槟分校(University of Illinois at Urbana-Champaign)研究生。进一步的修改和增强是在古川康隆(Yasutaka Furukawa)在华盛顿大学(University of Washington)做博士后时进行的。

该软件是在华盛顿大学Brian Curless教授和Steve Seitz教授以及微软研究院Richard Szeliski的指导下，古川康孝(Yasutaka Furukawa)在华盛顿大学博士后期间开发的。

多视图立体软件PMVS2包含在CMVS包中，是古川康隆(Yasutaka Furukawa)在伊利诺伊大学香槟分校(University of Illinois at Urbana-Champaign)和巴黎高等师范学院(Ecole Normale Superieure)的Jean Ponce教授指导下开发的。古川康隆是伊利诺伊大学香槟分校(University of Illinois at Urbana-Champaign)研究生。进一步的修改和增强是在古川康隆(Yasutaka Furukawa)在华盛顿大学(University of Washington)做博士后时进行的。

Industrial Light & Magic、Weta Digital和谷歌Inc.将PMVS2用于实际生产目的。Industrial Light & Magic、Weta Digital和谷歌Inc.将PMVS2用于实际生产目的。

2.2 功能与示例

从四个角度拍摄一个物体，并构建出目标的三维模型：

成果如下：

三·镇静剂——理想与现实

序列	问题
3.1	CMVS是否可用？
3.2	CMVS是否符合预期要求？
3.3	CMVS二次开发难度与上限是多少？
3.4	CMVS解算出来的模型是否具有足够的精度，是否能进行数据提取？
3.5	CMVS模型的二次解译？

以上即为使用该开源模型需要考虑的部分关键问题。

四·参考文献

[1]ayayayayo. 学习记录之三维重建2：cmvs稠密点云重建的实现[OL]. CSDN. 2020-02-12.