Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting- Completing M.C Escher's Print Gallery
Lucia Cipolina-Kun, Simone Caenazzo, Gaston Mazzei
TL;DR
This paper compares three advanced inpainting models—CoModGANs, LaMa, and GLIDE—for restoring large missing regions in digital art, using Escher's Print Gallery as a challenging test case.
Contribution
It provides a comprehensive qualitative and quantitative comparison of these models specifically for art restoration tasks involving large missing areas.
Findings
CoModGANs achieved the best inpainting quality.
LaMa showed superior performance in handling blurry regions.
GLIDE demonstrated competitive results with efficient processing.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Processing and 3D Reconstruction · Cultural Heritage Materials Analysis · Generative Adversarial Networks and Image Synthesis
MethodsInpainting · Guided Language to Image Diffusion for Generation and Editing · Softmax · Tanh Activation · Low-Rank Factorization-based Multi-Head Attention