VRST '00 Proceedings of the ACM symposium on Virtual reality software and technology
Placing three-dimensional models in an uncalibrated single image of an architectural scene
VRST '02 Proceedings of the ACM symposium on Virtual reality software and technology
Scalable Extrinsic Calibration of Omni-Directional Image Networks
International Journal of Computer Vision
Sensitivity of Calibration to Principal Point Position
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Layer Extraction with a Bayesian Model of Shapes
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Using Points at Infinity for Parameter Decoupling in Camera Calibration
IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM SIGGRAPH 2005 Papers
Extraction, matching, and pose recovery based on dominant rectangular structures
Computer Vision and Image Understanding
Placing Three-Dimensional Models in an Uncalibrated Single Image of an Architectural Scene
Presence: Teleoperators and Virtual Environments
What can we learn about the scene structure from three orthogonal vanishing points in images
Pattern Recognition Letters
Extraction, matching, and pose recovery based on dominant rectangular structures
Computer Vision and Image Understanding
Photo-consistent planar patches from unstructured cloud of points
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Three dimensional reconstruction of structured scenes based on vanishing points
PCM'06 Proceedings of the 7th Pacific Rim conference on Advances in Multimedia Information Processing
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
Editor's Choice Article: Image-consistent patches from unstructured points with J-linkage
Image and Vision Computing
Hi-index | 0.00 |
We address the problem of recovering 3D models from uncalibrated images of architectural scenes. We propose a simple, geometrically intuitive method which exploits the strong rigidity constraints of parallelism and orthogonality present in indoor and outdoor architectural scenes. We show how these simple constraints can be used to calibrate the cameras and to recover the projection matrices for each viewpoint.The projection matrices are used to recover partial 3D models of the scene and these can be used to visualise new viewpoints. Our approach does not need any {\it a priori} information about the cameras being used.A working system called {\em PhotoBuilder} had been designed and implemented to allow a user to interactively build a VRML model of a building from uncalibrated images from arbitrary viewpoints.