Modeling Realistic Degradations in Non-Blind Deconvolution

@article{Anger2018ModelingRD,
  title={Modeling Realistic Degradations in Non-Blind Deconvolution},
  author={J{\'e}r{\'e}my Anger and Mauricio Delbracio and Gabriele Facciolo},
  journal={2018 25th IEEE International Conference on Image Processing (ICIP)},
  year={2018},
  pages={978-982}
}
  • Jérémy Anger, Mauricio Delbracio, Gabriele Facciolo
  • Published 2018
  • Computer Science
  • 2018 25th IEEE International Conference on Image Processing (ICIP)
  • Most image deblurring methods assume an over-simplistic image formation model and as a result are sensitive to more realistic image degradations. We propose a novel variational framework, that explicitly handles pixel saturation, noise, quantization, as well as non-linear camera response function due to e.g., gamma correction. We show that accurately modeling a more realistic image acquisition pipeline leads to significant improvements, both in terms of image quality and PSNR. Furthermore, we… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 15 REFERENCES

    Stochastic Deconvolution

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Handling outliers in non-blind image deconvolution

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Stochastic Blind Motion Deblurring

    VIEW 1 EXCERPT

    Recent Progress in Image Deblurring

    VIEW 1 EXCERPT

    Deconvolving Images With Unknown Boundaries Using the Alternating Direction Method of Multipliers

    VIEW 2 EXCERPTS

    Nonlinear Camera Response Functions and Image Deblurring: Theoretical Analysis and Practice

    VIEW 1 EXCERPT