Stochastic Attribute Modeling for Face Super-Resolution

TL;DR

This paper introduces a stochastic attribute modeling approach for face super-resolution that explicitly accounts for uncertainty, leading to sharper images and outperforming existing methods.

Contribution

It proposes a novel face super-resolution scheme that encodes stochastic attributes and predicts them from LR images, addressing the uncertainty issue in HR image reconstruction.

Findings

Reduces uncertainty in face super-resolution

Outperforms state-of-the-art methods

Produces sharper HR images

Abstract

When a high-resolution (HR) image is degraded into a low-resolution (LR) image, the image loses some of the existing information. Consequently, multiple HR images can correspond to the LR image. Most of the existing methods do not consider the uncertainty caused by the stochastic attribute, which can only be probabilistically inferred. Therefore, the predicted HR images are often blurry because the network tries to reflect all possibilities in a single output image. To overcome this limitation, this paper proposes a novel face super-resolution (SR) scheme to take into the uncertainty by stochastic modeling. Specifically, the information in LR images is separately encoded into deterministic and stochastic attributes. Furthermore, an Input Conditional Attribute Predictor is proposed and separately trained to predict the partially alive stochastic attributes from only the LR images. Extensive evaluation shows that the proposed method successfully reduces the uncertainty in the learning process and outperforms the existing state-of-the-art approaches.