|
Photo Zoom
|
|
| Home | Team | Research | Teaching | Publications |
We present a system to automatically construct high resolution images from an unordered set of low resolution photos. It consists of an automatic preprocessing step to establish correspondences between any given photos. The user may then choose one image and the algorithm automatically creates a higher resolution result, several octaves larger up to the desired resolution. Our recursive creation scheme allows to transfer specific details at subpixel positions of the original image. It adds plausible details to regions not covered by any of the input images and eases the acquisition for large scale panoramas spanning different resolution levels.
|
Martin Eisemann
and
Marcus Magnor:
"ZIPMAPS: Zoom-Into-Parts Texture Maps", in Proc. Vision, Modeling and Visualization (VMV) 2010, Siegen, Germany, pp. 291–297, November 2010. Part of project "Photo Zoom". [pdf] [bib] In this paper, we propose a method for rendering highly detailed close-up views of arbitrary textured surfaces. Our hierarchical texture representation can easily be rendered in real-time, enabling zooming into specific texture regions to almost arbitrary magnification. To augment the texture map locally with high-resolution information, we describe how to automatically, seamlessly merge unregistered images of different scales. Our method is useful wherever close-up renderings of specific regions shall be provided, without the need for excessively large texture maps. |
|
Martin Eisemann,
Elmar Eisemann,
Hans-Peter Seidel,
and
Marcus Magnor:
"Photo Zoom: High Resolution from Unordered Image Collections", Poster at Siggraph, July 2010. Semi-Finalist in the Student Research Competition Part of project "Photo Zoom". [bib] |
|
Martin Eisemann,
Elmar Eisemann,
Hans-Peter Seidel,
and
Marcus Magnor:
"Photo Zoom: High Resolution from Unordered Image Collections", in Proc. Graphics Interface (GI) 2010, Ottawa, Canada, pp. 71–78, May 2010. Part of project "Photo Zoom". [pdf] [bib] We present a system to automatically construct high resolution images from an unordered set of low resolution photos. It consists of an automatic preprocessing step to establish correspondences between any given photos. The user may then choose one image and the algorithm automatically creates a higher resolution result, several octaves larger up to the desired resolution. Our recursive creation scheme allows to transfer specific details at subpixel positions of the original image. It adds plausible details to regions not covered by any of the input images and eases the acquisition for large scale panoramas spanning different resolution levels. |
|
Martin Eisemann
and
Marcus Magnor:
"ZIPMAPs: Zoom-into-parts texture maps", Technical Report no. 8, Computer Graphics Lab, TU Braunschweig, November 2008. Part of project "Photo Zoom". [pdf] [bib] In this paper, we propose a method for rendering highly detailed close-up views of arbitrary textured surfaces. Our hierarchical texture representation can easily be rendered in real-time, enabling zooming into specific texture regions to almost arbitrary magnification. To augment the texture map locally with high-resolution information, we describe how to automatically, seamlessly merge unregistered images of different scales. Our method is useful wherever close-up renderings of specific regions shall be provided, without the need for excessively large texture maps. |

TU Braunschweig
- Fakultät für Mathematik und Informatik
- Computer Graphics
- Research Projects
- Photo Zoom