TY - JOUR
T1 - Image reproduction based on texture image extension with traced drawing for heavy damaged mural painting
AU - Kawanaka, Haruki
AU - Kosaka, Shinichi
AU - Iwahori, Yuji
AU - Sugiyama, Saburo
N1 - Funding Information:
Kawanaka’s research was supported by JSPS Grant-in-Aid for Young Scientists (B) (22720291) and The Hori Sciences and Arts Foundation in Japan. Iwahori’s research is supported by JSPS Grant-in-Aid for Scientific Research (C) (23500228) and Chubu University Grant.
PY - 2013
Y1 - 2013
N2 - Not only geometric information but also optical information is needed to reproduce ruins using three-dimensional realistic computer graphics as they were when those were founded. In order to give a model a sense of reality, it is common to carry out the texture mapping of the photographed image. However such information can not be acquired from either weathered or partially destroyed ruins. While there are various conventional techniques for image restoration, which can overcome in the case of small missing and cracks, it is difficult to restore such a heavy damaged mural painting well when there is no information from the periphery. In this paper, we propose an image reproduction of a heavy damaged mural painting using a texture information extracted from another mural painting which has actually been restored by conservators and a traced drawing which the specialist guessed and drew. The restored image was used same pigment inks. Based on texture information from the restored image and a segmented traced drawing, we produce a restored image by applying the texture extension to each segment.
AB - Not only geometric information but also optical information is needed to reproduce ruins using three-dimensional realistic computer graphics as they were when those were founded. In order to give a model a sense of reality, it is common to carry out the texture mapping of the photographed image. However such information can not be acquired from either weathered or partially destroyed ruins. While there are various conventional techniques for image restoration, which can overcome in the case of small missing and cracks, it is difficult to restore such a heavy damaged mural painting well when there is no information from the periphery. In this paper, we propose an image reproduction of a heavy damaged mural painting using a texture information extracted from another mural painting which has actually been restored by conservators and a traced drawing which the specialist guessed and drew. The restored image was used same pigment inks. Based on texture information from the restored image and a segmented traced drawing, we produce a restored image by applying the texture extension to each segment.
KW - Extending texture
KW - Image inpainting
KW - Image restoration
KW - Poisson image editing
KW - Traced drawing
UR - http://www.scopus.com/inward/record.url?scp=84896941174&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84896941174&partnerID=8YFLogxK
U2 - 10.1016/j.procs.2013.09.181
DO - 10.1016/j.procs.2013.09.181
M3 - Conference article
AN - SCOPUS:84896941174
SN - 1877-0509
VL - 22
SP - 968
EP - 975
JO - Procedia Computer Science
JF - Procedia Computer Science
T2 - 17th International Conference in Knowledge Based and Intelligent Information and Engineering Systems, KES 2013
Y2 - 9 September 2013 through 11 September 2013
ER -