DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting - Archive ouverte HAL
Communication Dans Un Congrès Année : 2020

DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting

Résumé

The degree of difficulty in image inpainting depends on the types and sizes of the missing parts. Existing image inpainting approaches usually encounter difficulties in completing the missing parts in the wild with pleasing visual and contextual results as they are trained for either dealing with one specific type of missing patterns (mask) or unilaterally assuming the shapes and/or sizes of the masked areas. We propose a deep generative inpainting network, named DeepGIN, to handle various types of masked images. We design a Spatial Pyramid Dilation (SPD) ResNet block to enable the use of distant features for reconstruction. We also employ Multi-Scale Self-Attention (MSSA) mechanism and Back Projection (BP) technique to enhance our inpainting results. Our Deep-GIN outperforms the state-of-the-art approaches generally, including two publicly available datasets (FFHQ and Oxford Buildings), both quantitatively and qualitatively. We also demonstrate that our model is capable of completing masked images in the wild.
Fichier principal
Vignette du fichier
2008.07173.pdf (15.03 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03014865 , version 1 (19-11-2020)

Identifiants

  • HAL Id : hal-03014865 , version 1

Citer

Chu-Tak Li, Wan-Chi Siu, Zhi-Song Liu, Li-Wen Wang, Daniel Pak-Kong Lun. DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting. The 2020 European Conference on Computer Vision, Sep 2020, Online, United Kingdom. ⟨hal-03014865⟩
30 Consultations
88 Téléchargements

Partager

More