ACM Home Page
Please provide us with feedback. Feedback
Interactive 3D architectural modeling from unordered photo collections
Full text MovMov (26:00),  PdfPdf (23.18 MB)
Source International Conference on Computer Graphics and Interactive Techniques archive
ACM SIGGRAPH Asia 2008 papers table of contents
Singapore
SESSION: Urban modelling table of contents
Article No. 159  
Year of Publication: 2008
ISSN:0730-0301
Also published in ...
Authors
Sudipta N. Sinha  UNC Chapel Hill
Drew Steedly  Microsoft Live Labs
Richard Szeliski  Microsoft Research
Maneesh Agrawala  UC Berkeley
Marc Pollefeys  ETH Zurich and UNC Chapel Hill
Sponsor
SIGGRAPH: ACM Special Interest Group on Computer Graphics and Interactive Techniques
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): n/a,   Downloads (12 Months): n/a,   Citation Count: 2
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1457515.1409112
What is a DOI?

ABSTRACT

We present an interactive system for generating photorealistic, textured, piecewise-planar 3D models of architectural structures and urban scenes from unordered sets of photographs. To reconstruct 3D geometry in our system, the user draws outlines overlaid on 2D photographs. The 3D structure is then automatically computed by combining the 2D interaction with the multi-view geometric information recovered by performing structure from motion analysis on the input photographs. We utilize vanishing point constraints at multiple stages during the reconstruction, which is particularly useful for architectural scenes where parallel lines are abundant. Our approach enables us to accurately model polygonal faces from 2D interactions in a single image. Our system also supports useful operations such as edge snapping and extrusions.

Seamless texture maps are automatically generated by combining multiple input photographs using graph cut optimization and Poisson blending. The user can add brush strokes as hints during the texture generation stage to remove artifacts caused by unmodeled geometric structures. We build models for a variety of architectural scenes from collections of up to about a hundred photographs.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

1
 
2
 
3
Baillard, C., and Zisserman, A. 2001. Automatic reconstruction of piecewise planar models from multiple views. In CVPR, 559--565.
 
4
 
5
 
6
7
 
8
 
9
El-Hakim, S., Whiting, E., and Gonzo, L. 2005. 3d modeling with reusable and integrated building blocks. The 7th Conference on Optical 3-D Measurement Techniques.
10
 
11
Gibson, S., Hubbold, R., Cook, J., and Howard, T. 2003. Interactive reconstruction of virtual environments from video sequences. Computers and Graphics 27, 2.
 
12
Goesele, M., Snavely, N., Curless, B., Hoppe, H., and Seitz, S. M. 2007. Multi-view stereo for community photo collections. In ICCV.
13
14
 
15
 
16
Lempitsky, V. S., and Ivanov, D. V. 2007. Seamless mosaicing of image-based texture maps. In CVPR.
17
18
19
 
20
 
21
 
22
Rother, C. 2002. A new approach for vanishing point detection in architectural environments. In BMVC, vol. 20, 382--391.
 
23
Sketchup. http://www.sketchup.com.
24
 
25
 
26
van den Hengel, A., Dick, A., Thormahlen, T., Torr, P. H. S., and B. Ward. 2006. Fitting multiple models to multiple images with minimal user interaction. In the Intl. Workshop on the Representation and use of Prior Knowledge in Vision.
27
 
28
 
29
30
 
31


Collaborative Colleagues:
Sudipta N. Sinha: colleagues
Drew Steedly: colleagues
Richard Szeliski: colleagues
Maneesh Agrawala: colleagues
Marc Pollefeys: colleagues