TY - CPAPER
KW - 3D models
KW - Archive systems
KW - Computational methods
KW - Computer Vision
KW - Content based retrieval
KW - Cultural heritages
KW - Cut-off
KW - Edge detection
KW - Erosion process
KW - Graph-cut
KW - Historic preservation
KW - Image reconstruction
KW - Multiple cameras
KW - Target object
KW - Texture image
KW - Texture mapping
KW - Textures
KW - Three dimensional
KW - Three dimensional computer graphics
KW - Video image
KW - View-dependent
KW - Volume intersection
AU - K. Hisatomi
AU - K. Tomiyama
AU - M. Katayama
AU - Y. Iwadate
AB - We are developing an archive system that can preserve Japanese traditional dramatic arts, such as "Noh", in the form of dynamic 3D models. Dynamic 3D models are models that are generated from video images captured by multiple cameras surrounding a target object for each frame. The archive system can provide an entire Noh scene from any viewpoint by synthesizing dynamic 3D models with a computer graphics model of a Noh stage. Dynamic 3D models are generated using the graph-cut algorithm but it has a problem that thin parts of the object are cut off. As most of actors of Japanese traditional dramatic arts wear a traditional costume with long sleeves and a fan, it is important to reconstruct thin parts to preserve the arts. We therefore introduced the constraint imposed by the silhouette edges and the core obtained by adaptive erosion process on the volume intersection. We also propose the method of texture mapping that three texture images are blended, to suppress the flickers caused by the view dependent texture mapping. We describe our archive system with the proposed methods and present the effectiveness of the methods.
C2 - IEEE Int. Conf. Comput. Vis. Workshops, ICCV Workshops
DO - 10.1109/ICCVW.2009.5457605
N1 - Journal Abbreviation: IEEE Int. Conf. Comput. Vis. Workshops, ICCV Workshops
N2 - We are developing an archive system that can preserve Japanese traditional dramatic arts, such as "Noh", in the form of dynamic 3D models. Dynamic 3D models are models that are generated from video images captured by multiple cameras surrounding a target object for each frame. The archive system can provide an entire Noh scene from any viewpoint by synthesizing dynamic 3D models with a computer graphics model of a Noh stage. Dynamic 3D models are generated using the graph-cut algorithm but it has a problem that thin parts of the object are cut off. As most of actors of Japanese traditional dramatic arts wear a traditional costume with long sleeves and a fan, it is important to reconstruct thin parts to preserve the arts. We therefore introduced the constraint imposed by the silhouette edges and the core obtained by adaptive erosion process on the volume intersection. We also propose the method of texture mapping that three texture images are blended, to suppress the flickers caused by the view dependent texture mapping. We describe our archive system with the proposed methods and present the effectiveness of the methods.
SN - 9781424444427 (ISBN)
SP - 923
EP - 930
TI - Method of 3D reconstruction using graph cuts, and its application to preserving intangible cultural heritage
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-77953184372&doi=10.1109%2fICCVW.2009.5457605&partnerID=40&md5=ee6b7b1b37027cff44a81e452d9c0271
ER -