Issue No. 06 - Nov.-Dec. (2011 vol. 31)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MCG.2011.67
Mathias Eitz , Technical University of Berlin
Ronald Richter , Technical University of Berlin
Kristian Hildebrand , Technical University of Berlin
Tamy Boubekeur , Telecom ParisTech
Marc Alexa , Technical University of Berlin
Photosketcher is an interactive system for progressively synthesizing novel images using only sparse user sketches as input. Photosketcher works on the image content exclusively; it doesn't require keywords or other metadata associated with the images. Users sketch the rough shape of a desired image part, and Photosketcher searches a large collection of images for it. The search is based on a bag-of-features approach that uses local descriptors for translation-invariant retrieval of image parts. Composition is based on user scribbles: from the scribbles, Photosketcher predicts the desired part using Gaussian mixture models and computes an optimal seam using graph cuts. To further reduce visible seams, users can blend the composite image in the gradient domain.
image databases, image retrieval, image segmentation, image synthesis, sketching, computer graphics, graphics and multimedia
K. Hildebrand, T. Boubekeur, R. Richter, M. Alexa and M. Eitz, "Photosketcher: Interactive Sketch-Based Image Synthesis," in IEEE Computer Graphics and Applications, vol. 31, no. , pp. 56-66, 2011.