Project Introduction
3D reconstruction from multiple images is the creation of three-dimensional
models from a set of images. It is the reverse process of obtaining 2D images
from 3D scenes.
The essence of an image is a projection from a 3D scene onto a 2D plane,
during which process the depth is lost. The 3D point corresponding to a
specific image point is constrained to be on the line of sight. From a single
image, it is impossible to determine which point on this line corresponds to
the image point. If two images are available, then the position of a 3D point
can be found as the intersection of the two projection rays. This process is
referred to as triangulation. The key for this process is the relations between
multiple views which convey the information that corresponding sets of
points must contain some structure and that this structure is related to the
poses and the calibration of the camera.
A Demo
Bundler+PMVS实现三维重建:
手机拍摄的图片:
重建结果图:
Bundler+PMVS+possion表面重建:
mve+texrecon实现三维重建 :
MVE:特征点的检测(sift)+相机参数估计(内参,外参)+稀疏重建(SFM)+稠密重建(三角剖分算法)+纹理映射(texrecon):
Group Members
- 刘子健 M201572360
- 李婷婷 M201572361
- 潘治鸿 M201572364
- 欧阳超 M201572328
实验分工
- 方案1:潘治鸿,欧阳超调试
- 方案2:刘子健,李婷婷调试
- 数据采集:欧阳超,李婷婷
- 网站维护:潘治鸿,刘子健
- PPT制作: 刘子健,李婷婷
- 答 辩:刘子健
Project Progress
2016.5.20 第一周
- 项目选题和网页制作;
- 阅读三维重建相关资料,了解三维重建的基本原理和流程;
基于立体视觉的三维重建流程图:
2016.5.28 第二周
- 阅读相关参考文献 Multi-camera scene reconstruction via graph cuts, In ECCV 2002,
Scene Reconstruction and Visualization from Internet Photo Collections, PhD Thesis, 2008;
- linux下配置环境,调试源码;
2016.6.5 第三周
- 参考文献 Photo Tourism: Exploring Photo Collections in 3D,调试Bundler源码链接,Bundler可以得到相机参数和稀疏点云;
PMVS源码链接;
- Bundler+PMVS实现三维重建(see demo);
2016.6.14 第四周
- 参考文献Fuhrmann, S., Langguth, F. Goesele, M.,: MVE - A multiview reconstruction
environment.GCH, (2014);
参考文献Michael Waechter, Nils Moehrle, and Michael Goesele In: European Conference on Computer Vision (ECCV 2014), Zürich, Switzerland, 6-12 Sept. 2014.
调试MVE+ texrecon 源码链接;
- MVE(包含多个不同功能软件的组合体):使用的是 SIFT 特征点进行检测, 然后估计相机参数, 并使用从运动恢复结构即 SFM
进行稀疏重建, 得到稀疏点云, 之后使用三角剖分算法进行稠密表面面片重建,最后使用 texrecon 程序进行纹理映射。(see demo);
流程图:
2016.6.17 第五周
1.整理实验结果,制作PPT,录制demo;
2.课堂答辩;
3.整理源码;