A deep residual network combining with facial structure prior information is proposed for the restoration of compressed face images.In the training phase,a pre recovery network for initial restoration of the overall structure of the face image is first trained.However,the pre recovery network without any prior information cannot handle the facial components with fine structure well.Therefore,five facial components,including eyes,eyebrows,nose,mouth,and face profile,are extracted baased on the pre recovery network,respectively,for training the detail enhancement networks for restoring the facial components.At the restoration stage,combining with the facial mask generated by detection results at key points,the corresponding network parameters are used for accurate restoration of different face components.Experimental results show that the proposed algorithm has higher PSNR and SSIM than the existing state of the art restoration approaches,and has clearer texture details on the face components,thus improving the vision of the restored face image effects. |