HIGH QUALITY 3D RECONSTRUCTION OF COMPLEX CULTURAL OBJECTS

Nowadays, many cultural heritage applications require a 3D reconstruction of complex real world objects. Due to the complexity of real world objects, 3D reconstruction is often very time consuming and involves in general much manual effort. Therefore we report in this paper on a novel automatic 3D reconstruction approach to create virtual models of real world objects from a set of images with high redundancy. The power of our approach can be derived from the fact that we utilize the given redundancy to solve one of the main problems in photogrammetry, namely the correspondence problem. On the other hand we focus on minimizing the human interaction during the modeling process. The reconstruction pipeline starts with an image acquisition step, which consists of taking handheld images of the object with a calibrated digital consumer camera with short baselines. The rest of the workflow is represented by four consecutive steps: automatic orientation, multiple image segmentation, dense matching and multiview texturing. We demonstrate the accuracy, robustness and effectiveness of our proposed approach on several different real world objects.

[1]  Roberto Cipolla,et al.  Reconstruction of Outdoor Sculptures from Silhouettes under Approximate Circular Motion of an Uncalibrated Hand-Held Camera , 2002, MVA.

[2]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3]  Michael Werman,et al.  Multiresolution Textures from Image Sequences , 1997, IEEE Computer Graphics and Applications.

[4]  Fabio Remondino,et al.  Image-based Automated Reconstruction of the Great Buddha of Bamiyan, Afghanistan , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[5]  Robert T. Collins,et al.  A space-sweep approach to true multi-image matching , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[7]  Kiriakos N. Kutulakos,et al.  A Theory of Shape by Space Carving , 2000, International Journal of Computer Vision.

[8]  Horst Bischof,et al.  Automatic Foreground Propagation in Image Sequences for 3D Reconstruction , 2005, DAGM-Symposium.

[9]  Joachim Bauer,et al.  High-quality texture reconstruction from multiple views , 2001, Comput. Animat. Virtual Worlds.

[10]  Janne Heikkilä,et al.  Geometric Camera Calibration Using Circular Control Points , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Bruno Lévy,et al.  Least squares conformal maps for automatic texture atlas generation , 2002, ACM Trans. Graph..

[12]  Li Zhang,et al.  Automatic reconstruction and visualization of a complex Buddha tower of Bayon, Angkor, Cambodia , 2001 .

[13]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Katsushi Ikeuchi,et al.  Consensus surfaces for modeling 3D objects from multiple range images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[15]  Michael Garland,et al.  Surface simplification using quadric error metrics , 1997, SIGGRAPH.

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

[17]  Marc Levoy,et al.  The digital Michelangelo project: 3D scanning of large statues , 2000, SIGGRAPH.

[18]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[19]  Ruigang Yang,et al.  Real-time consensus-based scene reconstruction using commodity graphics hardware , 2002, 10th Pacific Conference on Computer Graphics and Applications, 2002. Proceedings..

[20]  Ruigang Yang,et al.  Real‐Time Consensus‐Based Scene Reconstruction Using Commodity Graphics Hardware † , 2003, Comput. Graph. Forum.

[21]  Stefano Soatto,et al.  Stereoscopic Segmentation , 2001, ICCV.

[22]  William A. Barrett,et al.  Intelligent scissors for image composition , 1995, SIGGRAPH.

[23]  Sabry F. El-Hakim,et al.  1 DETAILED 3D RECONSTRUCTION OF MONUMENTS USING MULTIPLE TECHNIQUES , 2002 .