Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting Completing M.C Escher's Print Gallery

Lucia Cipolina-Kun, Simone Caenazzo, Gaston Mazzei

CVPRW 2022 pp. 715-723

doi:10.1109/CVPRW56347.2022.00087 /cvprw/2022/cipolinakun2022cvprw-comparison/

Abstract

Digital art restoration has benefited from inpainting models to correct the degradation or missing sections of a painting. This work compares three current state-of-the art models for inpainting of large missing regions. We provide qualitative and quantitative comparison of the performance by CoModGANs, LaMa and GLIDE in inpainting of blurry and missing sections of images. We use Escher’s incomplete painting Print Gallery as our test study since it presents several of the challenges commonly present in restorative inpainting.

PDF CVPRW Semantic Scholar

Cite

Text

Cipolina-Kun et al. "Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting Completing M.C Escher's Print Gallery." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00087

Markdown

[Cipolina-Kun et al. "Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting Completing M.C Escher's Print Gallery." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/cipolinakun2022cvprw-comparison/) doi:10.1109/CVPRW56347.2022.00087

BibTeX

@inproceedings{cipolinakun2022cvprw-comparison,
  title     = {{Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting Completing M.C Escher's Print Gallery}},
  author    = {Cipolina-Kun, Lucia and Caenazzo, Simone and Mazzei, Gaston},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {715-723},
  doi       = {10.1109/CVPRW56347.2022.00087},
  url       = {https://mlanthology.org/cvprw/2022/cipolinakun2022cvprw-comparison/}
}