Texture optimization for example-based synthesis

@inproceedings{Kwatra2005TextureOF,
  title={Texture optimization for example-based synthesis},
  author={Vivek Kwatra and Irfan Essa and Aaron Bobick and Nipun Kwatra},
  booktitle={SIGGRAPH '05},
  year={2005}
}
We present a novel technique for texture synthesis using optimization. We define a Markov Random Field (MRF)-based similarity metric for measuring the quality of synthesized texture with respect to a given input sample. This allows us to formulate the synthesis problem as minimization of an energy function, which is optimized using an Expectation Maximization (EM)-like algorithm. In contrast to most example-based techniques that do region-growing, ours is a joint optimization approach that… CONTINUE READING
Highly Influential
This paper has highly influenced 71 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 693 citations. REVIEW CITATIONS
394 Citations
5 References
Similar Papers

Citations

Publications citing this paper.

693 Citations

0204060'07'10'13'16
Citations per Year
Semantic Scholar estimates that this publication has 693 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-5 of 5 references

The EM algorithm and extensions

  • G. MCLACHLAN, T. KRISHNAN
  • Wiley series in probability and statistics. John…
  • 1997
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…