Information Technology Reference
In-Depth Information
5 Conclusion
In this chapter, a texture synthesis algorithm particularly for composite textures is
proposed. The algorithm takes a sample texture image as input and outputs a larger
image filled with the same texture from the sample. The synthesis process is
controlled by a target image which has the same size as the output image and yields
a similar layout as the input. Due to the guidance of the target image, the output
image looks similar as the input globally and is composed of the same texture. The
proposed texture synthesis method can produce much more pleasant-looking results
for natural images than state-of-the-art texture synthesis techniques. For images
composed of both a non-texture foreground object and a textured background, an
additional object segmentation step is applied to differentiate the foreground from
background. Controlled texture synthesis is used for the background texture and
normal image up-scaling techniques are utilized on the foreground object to
preserve the scale of the object.
References
1.
Efros, A., Leung, T.: Texture Synthesis by Non-parametric Sampling. In: Proc. IEEE
International Conference on Computer Vision, Corfu, Greece (1999)
2.
Wei, L., Levoy, M.: Fast Texture Synthesis using Tree-structured Vector Quantization.
In: Proc. ACM 27th International Conference on Computer Graphics and Interactive
Techniques, New Orleans, Louisiana, USA (2000)
3.
Ashikhmin, M.: Synthesizing Natural Textures. In: Proc. ACM Symposium on
Interactive 3D Graphics, Research Triangle Park, North Carolina, USA (2001)
4.
Efros, A., Freeman, W.: Image Quilting for Texture Synthesis and Transfer. In: Proc.
ACM 28th International Conference on Computer Graphics and Interactive Techniques,
Los Angeles, CA, USA (2001)
5.
Kwatra, V., Schodl, A., Essa, I., Turk, G., Bobick, A.: Graphcut Textures: Image and
Video Synthesis Using Graph Cuts. In: Proc. ACM 30th International Conference on
Computer Graphics and Interactive Techniques, San Diego, CA, USA (2003)
6.
Kilshau, S., Drew, M., Moller, T.: Full search content independent block matching based
on the fast fourier transform. In: Proc. IEEE International Conference on Image
Processing, Rochester, NY, USA (2002)
7.
Mortensen, E., Barrett, W.: Intelligent Scissors for Image Composition. In: Proc. ACM
22nd International Conference on Computer Graphics and Interactive Techniques, Los
Angeles, CA, USA (1995)
8.
Perez, P., Gangnet, M., Blake, A.: Poisson Image editing. ACM Transactions on
Graphics 22(3), 313-318 (2003)
