Recovering variations in facial albedo from low resolution images

Abstract

Recovering facial albedo from low quality face images is a challenging task which arises when face recognition is attempted in the wild. Low quality of facial images is usually caused by extrinsic factors such as low resolution and noises, and intrinsic ones such as expressions. Existing research recovers facial albedo by dealing with the extrinsic and intrinsic factors separately. However, it is more natural and potentially more useful to approach albedo recovery by removing the two effects simultaneously.In this paper, we present a novel framework which can recover facial albedo by jointly solving these for both the extrinsic and intrinsic sources of uncertainty. This framework models albedo recovery problem by a joint optimization process which alternatively

Wavelet-Integrated Deep Networks for Single Image Super-Resolution

“…Here, the task is to recover the original high-resolution (HR) image from a single observation of the low-resolution (LR) image. This method is generally used in applications where the HR images are of importance, such as brain image enhancement [1], biometric image enhancement [2], face image enhancement [3], and standard-definition television (SDTV) and high definition television (HDTV) applications [4]. The problem of SISR is considered a highly ill-posed problem, because the number of unknown variables from an HR image is much higher compared to the known ones from an LR image.…”