Neural Image Recolorization for Creative Domains

Boyi Li, Serge J. Belongie, Ser-Nam Lim, Abe Davis

Abstract

We present a self-supervised approach to recolorization of images from design-oriented domains. Our approach can recolor images based on image exemplars or target color palettes provided by a user. In contrast with previous approaches, our method can reproduce color palettes with luminance distributions that differ significantly from input, and our method is the first palette-based approach to distinguish between recolorings that match reflectance and those that match illumination, making it particularly well-suited to visualizing different aesthetic decisions in design applications. The key to our approach is first to learn latent representations for texture and color in a setting where self-supervision is especially straightforward, and then to learn a mapping to our color representation from input color palettes and scene illumination, which offers a more intuitive space for controlling and exploring recolorization.
BibTeX
@inproceedings{li2022neural,
  author = {Boyi Li and Serge J. Belongie and Ser-Nam Lim and Abe Davis},
  title = {{Neural Image Recolorization for Creative Domains}},
  booktitle = {Workshops @ CVPR},
  year = {2022},
  doi = {10.1109/cvprw56347.2022.00242},
}

Loading related content...

Figure