Constructing a 3D trunk model from two images
Graphical Models
Image and Vision Computing
On-line modeling for real-time 3D target tracking
Machine Vision and Applications
Reconstruction of 3D curves for quality control
SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Energy-based reconstruction of 3D curves for quality control
EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Two-view curve reconstruction based on the snake model
Journal of Computational and Applied Mathematics
High-Order differential geometry of curves for multiview reconstruction and matching
EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
| Hi-index | 0.00 |
Is the real problem in resolving correspondence using currentstereo algorithms the lack of the "right" matching criterion?In studying the related task of reconstructing three-dimensionalspace curves from their projections in multipleviews, we suggest that the problem is more basic: matchingand reconstruction are coupled, and so reconstruction algorithmsshould exploit this rather than assuming that matchingcan be successfully performed before reconstruction. Torealize this coupling, a generative model of curves is introducedwhich has two key components: (i) a prior distributionof general space curves and (ii) an image formation modelwhich describes how 3D curves are projected onto the imageplane. A novel aspect of the image formation model is that ituses an exact description of the gradient field of a piecewiseconstant image. Based on this forward model, a fully automaticalgorithm for solving the inverse problem is developedfor an arbitrary number of views. The resulting algorithmis robust to partial occlusion, deficiencies in image curveextraction and it does not rely on photometric information.The relative motion of the cameras is assumed to be given.Several experiments are carried out on various realistic scenarios.In particular, we focus on scenes where traditionalcorrelation-based methods would fail.