A High-Performance Face Illumination Processing Method via Multi-Stage Feature Maps

Abstract

In recent years, Generative Adversarial Networks (GANs)-based illumination processing of facial images has made favorable achievements. However, some GANs-based illumination-processing methods only pay attention to the image quality and neglect the recognition accuracy, whereas others only crop partial face area and ignore the challenges to synthesize photographic face, background and hair when the original face image is under extreme illumination (Image under extreme illumination (extreme illumination conditions) means that we cannot see the texture and structure information clearly and most pixel values tend to 0 or 255.). Moreover, the recognition accuracy is low when the faces are under extreme illumination conditions. For these reasons, we present an elaborately designed architecture based on convolutional neural network and GANs for processing the illumination of facial image. We use ResBlock at the down-sampling stage in our encoder and adopt skip connections in our generator. This special design together with our loss can enhance the ability to preserve identity and generate high-quality images. Moreover, we use different convolutional layers of a pre-trained feature network to extract varisized feature maps, and then use these feature maps to compute loss, which is named multi-stage feature maps (MSFM) loss. For the sake of fairly evaluating our method against state-of-the-art models, we use four metrics to estimate the performance of illumination-processing algorithms. A variety of experimental data indicate that our method is superior to the previous models under various illumination challenges in illumination processing. We conduct qualitative and quantitative experiments on two datasets, and the experimental data indicate that our scheme obviously surpasses the state-of-the-art algorithms in image quality and identification accuracy.

Deep Portrait Delighting

“…However, relying on parametric models limits their ability to capture non-facial or high-frequency details. Recent deep-learning methods tackle this problem using feature-wise perceptual losses [27] or closed-loop GANs [16] to recover facial details. A drawback of all these methods however is that they either focus exclusively on face regions, perform only one aspect of the delighting process (e.g.…”

Face illumination processing via dense feature maps and multiple receptive fields

“…Experiment results: In this section, we compare the state-of-the-art methods such as Ling et al [14], CycleGAN [15], EDIT [16], Pix2Pix [17] with ours. Moreover, we conduct a lot of objective evaluations by using SSIM [22], MS-SSIM [23], FSIM [24] and identification accuracy.…”

“…Ling et al [13] normalises face illumination by instance normalisation based on fixed gamma value and GANs. Ling et al [14] processes face illumination by using multi-stage feature maps loss and residual block at down-sampling and their method obtain good image quality and high recognition accuracy.…”

“…Ling et al. [14] processes face illumination by using multi‐stage feature maps loss and residual block at down‐sampling and their method obtain good image quality and high recognition accuracy.…”

De-lighting Human Images Using Region-Specific Data Augmentation

“…However, their reliance on parametric models restricted their ability to capture non-facial details and high-frequency intricacies. More recent deep learning methods have addressed this limitation by utilizing feature-wise perceptual losses [20] or employing closed-loop Generative Adversarial Networks (GANs) [13] to recover finer facial details. Nevertheless, a drawback common to these methods is that they tend to focus solely on facial regions, address only specific aspects of the de-lighting process (e.g.…”