Abstract
This paper presents a novel method for automatically recovering dense surface patches using large sets (1000’s) of calibrated images taken from arbitrary positions within the scene. Physical instruments, such as Global Positioning System (GPS), inertial sensors, and inclinometers, are used to estimate the position and orientation of each image. Some of the most important characteristics of our approach are that it: 1) uses and refines noisy calibration estimates; 2) compensates for large variations in illumination; 3) tolerates significant soft occlusion (e.g. tree branches); and 4) associates, at a fundamental level, an estimated normal (eliminating the frontal-planar assumption) and texture with each surface patch.
This paper describes research done at the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology and was supported in part by the Advanced Research Projects Agency of the Department of the Defense under Once of Naval Research contract N00014-91-J-4038 and Rome Lab contract F3060-94-C-0204.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Shawn Becker and V. Michael Bove, Jr. Semiautomatic 3-D model extraction from uncalibrated 2-D camera views. In Visual Data Exploration and Analysis, volume 2410, pages 447–461. SPIE, February 1995. San Jose, CA.
R. Collins, C. Jaynes, F. Stolle, X. Wang, Y. Cheng, A. Hanson, and E. Riseman. A system for automated site model acquisition. In Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision II, volume 7617. SPIE, April 1995. Orlando, FL.
Robert T. Collins. A space-sweep approach to true multi-image matching. In Computer Vision and Pattern Recognition (CVPR’ 96 Proceedings), pages 358–363, June 1996. San Francisco, CA.
Satyan Coorg. Pose Imagery and Automated 3-D Modeling of Urban Environments. PhD thesis, MIT, 1998.
Satyan Coorg, Neel Master, and Seth Teller. Acquisition of a large pose-mosaic dataset. In Computer Vision and Pattern Recognition (CVPR’ 98 Proceedings), pages 872–878, June 1998. Santa Barbara, CA.
Douglas S. J. De Couto. Instrumentation for rapidly acquiring pose-imagery. Master’s thesis, MIT, 1998.
Paul E. Debevec, Camillo J. Taylor, and Jitendra Malik. Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach. In Computer Graphics (SIGGRAPH’ 96 Proceedings), pages 11–20, August 1996.
Kiriakos N. Kutulakos and Steven M. Seitz. A theory of shape by space carving. CS Technical Report 692, University of Rochester, May 1998.
Kiriakos N. Kutulakos and Steven M. Seitz. What do n photographs tell us about 3D shape? CS Technical Report 680, University of Rochester, January 1998.
J.P. Mellor. Automatically recovering geometry and texture from large sets of calibrated images. Technical Report AITR-1674, MIT, October 1999.
J.P. Mellor, Seth Teller, and Tomás Lozano-Pérez. Dense depth maps from epipolar images. In Image Understanding Workshop (IUW’ 97 Proceedings), volume 2, pages 893–900, May 1997. New Orleans, LA.
J.P. Mellor, Seth Teller, and Tomás Lozano-Pérez. Dense surface patches from thousands of pose images. In Image Understanding Workshop (IUW’ 98 Proceedings), volume 2, pages 537–542, November 1998. Monterey, CA.
Steven M. Seitz and Charles R. Dyer. Photorealistic scene reconstruction by voxel coloring. In Computer Vision and Pattern Recognition (CVPR’ 97 Proceedings), pages 1067–1073, 1997. Puerto Rico.
Heung-Yeung Shum, Mei Han, and Richard Szeliski. Interactive construction of 3D models from panoramic mosaics. In Computer Vision and Pattern Recognition (CVPR’ 98 Proceedings), pages 427–433, June 1998. Santa Barbara, CA.
Richard Szeliski and David Tonnesen. Surface modeling with oriented particle systems. In Computer Graphics (SIGGRAPH’ 92 Proceedings), volume 26, pages 185–194, July 1992.
Seth Teller. Automated urban model acquisition: Project rationale and status. In Image Understanding Workshop (IUW’ 98 Proceedings), volume 2, pages 455–462, November 1998. Monterey, CA.
Seth Teller. Toward urban model acquisition from geo-located images. In Pacific Graphics’ 98, 1998. Singapore.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mellor, J. (2001). Geometry and Texture from Thousands of Images. In: Pollefeys, M., Van Gool, L., Zisserman, A., Fitzgibbon, A. (eds) 3D Structure from Images — SMILE 2000. SMILE 2000. Lecture Notes in Computer Science, vol 2018. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45296-6_12
Download citation
DOI: https://doi.org/10.1007/3-540-45296-6_12
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41845-0
Online ISBN: 978-3-540-45296-6
eBook Packages: Springer Book Archive