Surface Reconstruction from Multi-View Stereo

We describe an original method to reconstruct a 3D scene from a sequence of images. Our approach uses both the dense 3D point cloud extracted by multi-view stereovision and the calibrated images. It combines depth-maps construction in the image planes with surface reconstruction through restricted Delaunay triangulation. The method may handle very large scale outdoor scenes. Its accuracy has been tested on numerous scenes including the dense multi-view benchmark proposed by Strecha et al. Our results compare favorably with the current state of the art.

[1]  Jan-Michael Frahm,et al.  Detailed Real-Time Urban 3D Reconstruction from Video , 2007, International Journal of Computer Vision.

[2]  Radim Sara,et al.  Depth Map Fusion with Camera Position Refinement , 2009 .

[3]  Radu Horaud,et al.  TransforMesh : A Topology-Adaptive Mesh-Based Approach to Surface Evolution , 2007, ACCV.

[4]  Takeo Kanade,et al.  Image-consistent surface triangulation , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[5]  S. B. Needleman,et al.  A general method applicable to the search for similarities in the amino acid sequence of two proteins. , 1970, Journal of molecular biology.

[6]  Mariette Yvinec,et al.  High resolution surface reconstruction from overlapping multiple-views , 2009, SCG '09.

[7]  Luc Van Gool,et al.  Combined Depth and Outlier Estimation in Multi-View Stereo , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Leif Kobbelt,et al.  Robust reconstruction of watertight 3D models from non-uniformly sampled point clouds without normal information , 2006, SGP '06.

[9]  Steve Oudot,et al.  Provably good sampling and meshing of surfaces , 2005, Graph. Model..

[10]  Pascal Fua,et al.  On benchmarking camera calibration and multi-view stereo for high resolution imagery , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Jean-Philippe Pons,et al.  Towards high-resolution large-scale multi-view stereo , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[13]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Michael Goesele,et al.  Multi-View Stereo for Community Photo Collections , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[15]  Adrian Hilton,et al.  Scene modelling from sparse 3D data , 2005, Image Vis. Comput..

[16]  C. Strecha,et al.  Wide-baseline stereo from multiple views: A probabilistic account , 2004, CVPR 2004.

[17]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[18]  Mariette Yvinec,et al.  Triangulations in CGAL (extended abstract) , 2000, SCG '00.

[19]  Hans-Peter Seidel,et al.  Multi-level partition of unity implicits , 2005, SIGGRAPH Courses.