Corpus ID: 218763285

Instance-aware Image Colorization

@article{Su2020InstanceawareIC,
  title={Instance-aware Image Colorization},
  author={Jheng-Wei Su and Hung-Kuo Chu and Jianzhong Huang},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10825}
}
  • Jheng-Wei Su, Hung-Kuo Chu, Jianzhong Huang
  • Published 2020
  • Computer Science
  • ArXiv
  • Image colorization is inherently an ill-posed problem with multi-modal uncertainty. Previous methods leverage the deep neural network to map input grayscale images to plausible color outputs directly. Although these learning-based methods have shown impressive performance, they usually fail on the input images that contain multiple objects. The leading cause is that existing models perform learning and colorization on the entire image. In the absence of a clear figure-ground separation, these… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES

    Deep exemplar-based colorization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Colorization

    VIEW 2 EXCERPTS

    Learning Diverse Image Colorization

    VIEW 1 EXCERPT

    Colorful Image Colorization

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Image colorization using similar images

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL