Can face image with partially or heavily occlusion be inpainted? In this paper, it is considered as a decision-making issue. An adaptive gating boosts multi-scale self-attention face image inpainting network is proposed to address the issues; it focuses on the task of inpainting large-area occluded face images in complex backgrounds including insufficient fine-grained texture synthesis, inaccurate color inpainting, and semantic dissonance. Multi-level dilated convolution group is constructed to capture local details and long-range contextual information with the help of a dual adaptive gating mechanism which works as: (1) multi-layer convolution and batch normalization to achieve spatially adaptive feature selection, replacing the traditional fixed fusion method of residual connections; (2) multi-scale self attention mechanism explicitly models the global pixel dependency relationship, solving the problems of structural coherence and fine-grained synthesis in large-scale defect inpainting. A large number of experiment results show that this method improves the PSNR and SSIM metrics by an average of 0 .284dB and 0 .0042 on the FFHQ dataset, and improves the FID by an average of 8 .265%. Especially in scenarios with large areas of occlusion ( >50%), the FID decreases by 3 .009, significantly improving the quality of facial image inpainting on complex backgrounds. The adaptive gating boosts multi-scale self-attention work strategy can provide reference for other decision-making issues.