Multi‐stage image inpainting using improved partial convolutions

Autor: Cheng Li, Dan Xu, Hao Zhang
Jazyk: angličtina
Rok vydání: 2024
Předmět:
Zdroj: IET Image Processing, Vol 18, Iss 12, Pp 3343-3355 (2024)
Druh dokumentu: article
ISSN: 1751-9667
1751-9659
DOI: 10.1049/ipr2.13178
Popis: Abstract In recent years, deep learning models have dramatically influenced image inpainting. However, many existing studies still suffer from over‐smoothed or blurred textures when missing regions are large or contain rich visual details. To restore textures at a fine‐grained level, a multi‐stage inpainting approach is proposed, which applies a series of partial inpainting modules as well as a progressive inpainting module to inpaint missing areas from their boundaries to the centre successively. Some improvements are made on the partial convolutions to reduce artifacts like blurriness, which require a convolution kernel to contain known pixels more than a certain proportion. Towards photorealistic inpainting results, the intermediate outputs from each stage are used to compute the loss. Finally, to facilitate the training process, a multi‐step training is designed that progressively adds inpainting modules to optimize the model. Experiments show that this method outperforms the current excellent techniques on the publicly available datasets: CelebA, Places2 and Paris StreetView.
Databáze: Directory of Open Access Journals
Externí odkaz: