Computer Graphics and Visualization › Publications › Interactive Geometry-Aware Segmentation for the Decomposition of Kaleidoscopic Images

In Proceedings of Vision, Modeling, and Visualization

Interactive Geometry-Aware Segmentation for the Decomposition of Kaleidoscopic Images

Oliver Klehm, I. Reshetouski, Elmar Eisemann, Hans-Peter Seidel, and Ivo Ihrke

a) Input: Kaleidoscope image. b) User-drawn mask (green checkerboard pattern). c) User-drawn mask isolated. d) Approximate visual hull generated from (c) using image-based shading. e) Resulting labeling via visual hull

Publisher Paper Cite More

Mirror systems have recently emerged as an alternative low-cost multi-view imaging solution. The use of these systems critically depends on the ability to compute the background of a multiply mirrored object. The images taken in such systems show a fractured, patterned view, making edge-guided segmentation difficult. Further, global illumination and light attenuation due to the mirrors make standard segmentation techniques fail. We therefore propose a system that allows a user to do the segmentation manually. We provide convenient tools that enable an interactive segmentation of kaleidoscopic images containing three-dimensional objects. Hereby, we explore suitable interaction and visualization schemes to guide the user. To achieve interactivity, we employ the GPU in all stages of the application, such as 2D/3D rendering as well as segmentation.

More Information

Publisher Paper preprint

Gallery

Citation

Oliver Klehm, I. Reshetouski, Elmar Eisemann, Hans-Peter Seidel, and Ivo Ihrke, Interactive Geometry-Aware Segmentation for the Decomposition of Kaleidoscopic Images, In Proceedings of Vision, Modeling, and Visualization, pp. 9–14, 2012.

BibTex 

@inproceedings{bib:klehm:2012,
    author       = { Klehm, Oliver and Reshetouski, I. and Eisemann, Elmar and Seidel, Hans-Peter and Ihrke, Ivo },    
    title        = { Interactive Geometry-Aware Segmentation for the Decomposition of Kaleidoscopic Images },
    booktitle    = { In Proceedings of Vision, Modeling, and Visualization },
    year         = { 2012 },
    pages        = { 9--14 },
    doi          = { 10.2312/PE/VMV/VMV12/009-014 },
    dblp         = { conf/vmv/KlehmRESI12 },
    url          = { https://publications.graphics.tudelft.nl/papers/306 },
}