Neural Image Recolorization for Creative Domains
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Neural Image Recolorization for Creative Domains. / Li, Boyi; Belongie, Serge; Lim, Ser Nam; Davis, Abe.
Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022. IEEE Computer Society Press, 2022. p. 2225-2229 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Vol. 2022-June).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Neural Image Recolorization for Creative Domains
AU - Li, Boyi
AU - Belongie, Serge
AU - Lim, Ser Nam
AU - Davis, Abe
N1 - Publisher Copyright: © 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
U2 - 10.1109/CVPRW56347.2022.00242
DO - 10.1109/CVPRW56347.2022.00242
M3 - Article in proceedings
AN - SCOPUS:85137773214
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 2225
EP - 2229
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
PB - IEEE Computer Society Press
T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Y2 - 19 June 2022 through 20 June 2022
ER -
ID: 344438935