ID face photos are widely used for identity verification in many business authentication situations. To avoid any infringement and misuse, the ID photos provided by the relevant government agencies and business organizations are always corrupted with designed watermarks, such as random wave lines or meshes. These corrupted images are further compressed with JPEG algorithm to reduce their storage size. The artifacts caused by the random meshes and JPEG compression seriously destroy the original image information and quality, which makes the face verification between the corrupted ID faces and daily life images extremely difficult. To tackle these issues, a preprocessing step called blind inpainting is needed to recover the corrupted ID faces. In this paper, we present a new framework to address this blind face inpainting problem. We use an improved Deep Recursive Residual Network (IDRRN) to learn an effective non-linear mapping between the corrupted and clean ID image pairs. To train the IDRRN model, a unified Euclidean loss function considering both 0- and 1st-order pixel residuals is proposed to enhance the image pixel as well as gradient reconstruction. In addition, we collect a dataset of clean ID images and develop a simulation procedure to generate corresponding corrupted ID face images. Final experiments demonstrate that the recovered ID face images inferred from our IDRRN model achieve the best performance in terms of perceptual error and verification accuracy.