Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting- Completing M.C Escher's Print Gallery
This is an incremental study that benchmarks existing methods for art restoration, addressing challenges in digital art inpainting for restoration applications.
This work compared three state-of-the-art inpainting models (CoModGANs, LaMa, and GLIDE) for restoring large missing regions in digital art, using M.C. Escher's incomplete 'Print Gallery' as a test case to evaluate their performance on blurry and missing sections.
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.