Presentation 2009-06-19
Super Resolution Texture Mapping from Multiview Images and Example Images
Masaaki IIYAMA, Koh KAKUSHO, Michihiko MINOH,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents an artifact-free super-resolution texture maping method from multiple view images. The multiple view images are upsampled with a learning-based super-resolution technique and are mapped onto a 3D mesh model. However, mapping multiview images onto a 3D model is not an easy task, because artifacts may appear when different upsampled images are mapped onto neighboring meshes. We define a cost function that becomes large when the artifacts appear on neighboring meshes, and our method searches the image-and-mesh assignment which minimizes the cost function. Experimental results with real images demonstrate the effectiveness of our method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Super resolution / Texture mapping / Graph cut
Paper # PRMU2009-54
Date of Issue

Conference Information
Committee PRMU
Conference Date 2009/6/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Super Resolution Texture Mapping from Multiview Images and Example Images
Sub Title (in English)
Keyword(1) Super resolution
Keyword(2) Texture mapping
Keyword(3) Graph cut
1st Author's Name Masaaki IIYAMA
1st Author's Affiliation Graduate School of Economics, Kyoto University()
2nd Author's Name Koh KAKUSHO
2nd Author's Affiliation School of Science and Technology, Kwansei Gakuin University
3rd Author's Name Michihiko MINOH
3rd Author's Affiliation Acamemic Center for Computing and Media Studies, Kyoto University
Date 2009-06-19
Paper # PRMU2009-54
Volume (vol) vol.109
Number (no) 88
Page pp.pp.-
#Pages 6
Date of Issue