Throwaway Shadows Using Parallel Encoders Generative Adversarial Network

Abstract

Face photographs taken on a bright sunny day or in floodlight contain unnecessary shadows of objects on the face. Most previous works deal with removing shadow from scene images and struggle with doing so for facial images. Faces have a complex semantic structure, due to which shadow removal is challenging. The aim of this research is to remove the shadow of an object in facial images. We propose a novel generative adversarial network (GAN) based image-to-image translation approach for shadow removal in face images. The first stage of our model automatically produces a binary segmentation mask for the shadow region. Then, the second stage, which is a GAN-based network, removes the object shadow and synthesizes the effected region. The generator network of our GAN has two parallel encoders—one is standard convolution path and the other is a partial convolution. We find that this combination in the generator results not only in learning an incorporated semantic structure but also in disentangling visual discrepancies problems under the shadow area. In addition to GAN loss, we exploit low level L1, structural level SSIM and perceptual loss from a pre-trained loss network for better texture and perceptual quality, respectively. Since there is no paired dataset for the shadow removal problem, we created a synthetic shadow dataset for training our network in a supervised manner. The proposed approach effectively removes shadows from real and synthetic test samples, while retaining complex facial semantics. Experimental evaluations consistently show the advantages of the proposed method over several representative state-of-the-art approaches.

Enhancing Rainy Weather Driving: Deep Unfolding Network With PGD Algorithm for Single Image Deraining

“…SPANet [30] utilizes an attention unit-based network model for removing rain in a local to global manner, etc. Currently, most deep learning methods use a fully supervised training model, but there is no shortage of excellent unsupervised and semi-supervised training networks [12], [13], [14], [15], [16]. Specifically, RR-GAN [12] employs an unsupervised training mode to obtain rain streak information, by using a recursive memory module that exploits attentional mechanisms using the multiscale attentional memory generator MAMG circular recursive.…”