Generation of 3D model with super resolved texture from image sequence

Kenji Nakamura, Hideo Saito, Shinji Ozawa

Research output: Contribution to journalConference article


In this paper, we propose a method for reconstruction of 3D shape with super resolved texture of book surface by integrating shape that is recovered from an image sequence taken with moving camera. The image sequence is divided into a number of blocks. The factorization method is applied to each block for obtaining a part of 3D shape of the object. The 3D shapes reconstructed from the block of the sequence are merged into one integrated 3D Model. In this time we generate super resolved texture using multiple images. For the merging, position and pose of each 3D shape is adjusted based on the surface normal of the overlapped area. The merged 3D model of all region of the book surface is shown for demonstrating the effectiveness of the proposed method. Furthermore we generate super resolved texture finer than original image using multiple images.

Original languageEnglish
Pages (from-to)1406-1411
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Publication statusPublished - 2000 Dec 1
Event2000 IEEE Interantional Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: 2000 Oct 82000 Oct 11


ASJC Scopus subject areas

  • Control and Systems Engineering
  • Hardware and Architecture

Cite this