3D Model Acquisition from Uncalibrated Images

In this paper we address the problem of recovering 3D models from uncalibrated images of architectural scenes. We propose a simple, geometrically intuitive method which exploits strong rigidity constraints such as parallelism and orthogonality present in indoor and outdoor architectural scences. We show how these simple constraints can be used to calibrate the cameras and to recover the 3 x 4 projection matrices for each viewIn this paper we propose a much simpler approach to construct a 3D model and generate new viewpoint images by exploiting strong constraints present in the scenes to be modelled. In the context of architectural environments, the constraints which can be used are parallelism and orthogonality. These constraints lead to very simple and geometrically intuitive methods to calibrate the cameras and to recover Euclidean models of the scene from only two images from arbitrary positions. point. The projection matrices are used to recover partial 3D models of the scene and these 2 Outline of the algorithm can be used to visualise new viewpoints. A 3D model can be recovered from two or more Our approach does not need any a priori in- uncalibrated images. Our algorithm consists of formation about the cameras being used. A the four following stages (see figure working system has been designed and implemented to allow the user to interactively build 1. We first define a set of primitives - segments a 3D model from a pair of uncalibrated images and cuboids - for which parallelism and orfrom arbitrary viewpoints. thogonality constraints are derived. These primitives are precisely localised in the image using the image gradient information.

[1]  Amnon Shashua,et al.  Trilinearity in Visual Recognition by Alignment , 1994, ECCV.

[2]  Andrew Zisserman,et al.  Resolving ambiguities in auto–calibration , 1998, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[3]  Reinhard Koch,et al.  Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  I HartleyRichard.  Lines and Points in Three Views and the Trifocal Tensor , 1997 .

[5]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[6]  S. P. Mudur,et al.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[7]  Richard I. Hartley,et al.  In defence of the 8-point algorithm , 1995, Proceedings of IEEE International Conference on Computer Vision.

[8]  Václav Hlavác,et al.  Rendering real-world objects using view interpolation , 1995, Proceedings of IEEE International Conference on Computer Vision.

[9]  Kenichi Kanatani,et al.  Statistical optimization for geometric computation - theory and practice , 1996, Machine intelligence and pattern recognition.

[10]  Roberto Cipolla,et al.  The visual motion of curves and surfaces , 1998, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[11]  Steven M. Seitz,et al.  Toward image-based scene representation using view morphing , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[12]  Takeo Kanade,et al.  Constructing virtual worlds using dense stereo , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[13]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[14]  Paul A. Beardsley,et al.  3D Model Acquisition from Extended Image Sequences , 1996, ECCV.

[15]  Andrew Zisserman,et al.  Metric rectification for perspective images of planes , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[16]  Richard Szeliski,et al.  The lumigraph , 1996, SIGGRAPH.

[17]  W. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[18]  Marc Levoy,et al.  Light field rendering , 1996, SIGGRAPH.

[19]  Jitendra Malik,et al.  Modeling and Rendering Architecture from Photographs: A hybrid geometry- and image-based approach , 1996, SIGGRAPH.