GPU Acceleration of Image Analogies

Masaki HIRAGA; Hidetoshi ANDO

doi:10.11371/aiieej.34vc.0.227.0

Proceedings of Visual Computing / Graphics and CAD Joint Symposium 2006

Session ID : 06-39

DOI https://doi.org/10.11371/aiieej.34vc.0.227.0

Conference information

Host: The Institute of Image Electronics Engineers of Japan

Co-host: Toho University, Tokyo Denki University, Nihon University, Chiba Institute of Technology, Information Processing Society of Japan

12:00-14:00 Poster Session Chair: Norimasa YOSHIDA, Nihon University

GPU Acceleration of Image Analogies

*Masaki HIRAGA, Hidetoshi ANDO

Author information

Keywords: Image Analogies, GPU Acceleration, K-means, Quad tree, Feature Vector Texture, Reference Texture

CONFERENCE PROCEEDINGS FREE ACCESS

Details

Abstract

Image Analogies algorithm performs a search of the tree to find a similar pixel in the training images. GPU’s architecture is unfit for the trees which require using stack or queue when a search is performed. To solve this issue, our method builds a quad tree by using K-means. The tree doesn’t need back-track to be searched. Hereby, the tree is suitable for GPU and we have achieved to accelerate Image Analogies with GPU.

Corresponding author

Register with J-STAGE for free!