This work exploits the basic denoising autoencoding (DAE) as enhanced priori for color image restoration (IR). The proposed method consists of two steps: enhanced DAE network learning and iterative restoration. To be special, at the training phase, a denoising network taking 6-dimensional variable as input is trained. Then, the network-driven high-dimensional prior information embedded DAE priori is utilized in the iterative restoration procedure. We first map the intermediate color image to be 6 dimensional and employ the higher-dimensional network to handle its corrupted version. The average operator is used to turn it back to the 3-channel image. The higher-dimensional prior alleviates the issue of the basic DAE that getting trapped in local optimal solution and effectively overcomes the instability. Experimental results on single image super-restoration (SISR) and deblurring demonstrate that the proposed algorithm can achieve good performance and prime visual inspection.