Image inpainting via spatial projections

作者:

Highlights:

• A novel architecture is proposed for image inpainting without any self-attention mechanism.

• A spatial projection layer is proposed to project the spatial information from non-hole regions to the hole regions for introducing efficient spatial consistency in the inpainted image.

• Unlike existing state-of-the-art architectures for image inpainting, we introduced the use the edge loss with Canny edge operator for better optimization of the proposed network.

• The comparison with existing state-of-the-art methods, detailed ablation study, user study and analysis on object removal task proves the superiority of proposed method over existing methods for image inpainting.

摘要

•A novel architecture is proposed for image inpainting without any self-attention mechanism.•A spatial projection layer is proposed to project the spatial information from non-hole regions to the hole regions for introducing efficient spatial consistency in the inpainted image.•Unlike existing state-of-the-art architectures for image inpainting, we introduced the use the edge loss with Canny edge operator for better optimization of the proposed network.•The comparison with existing state-of-the-art methods, detailed ablation study, user study and analysis on object removal task proves the superiority of proposed method over existing methods for image inpainting.

论文关键词:Spatial projections,Inpainting,Object removal

论文评审过程:Received 6 June 2022, Revised 29 August 2022, Accepted 11 September 2022, Available online 13 September 2022, Version of Record 17 September 2022.

论文官网地址:https://doi.org/10.1016/j.patcog.2022.109040