ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
This work addresses the problem of improving image quality by removing shadows, which is important for applications like computer vision and photography, but it appears incremental as it builds on existing GAN and attention mechanisms.
The paper tackles shadow detection and removal in images by proposing ARGAN, an attentive recurrent generative adversarial network, which outperforms state-of-the-art methods on four public datasets, producing more realistic results, especially in recovering shadow details.
In this paper we propose an attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image. The generator consists of multiple progressive steps. At each step a shadow attention detector is firstly exploited to generate an attention map which specifies shadow regions in the input image.Given the attention map, a negative residual by a shadow remover encoder will recover a shadow-lighter or even a shadow-free image. A discriminator is designed to classify whether the output image in the last progressive step is real or fake. Moreover, ARGAN is suitable to be trained with a semi-supervised strategy to make full use of sufficient unsupervised data. The experiments on four public datasets have demonstrated that our ARGAN is robust to detect both simple and complex shadows and to produce more realistic shadow removal results. It outperforms the state-of-the-art methods, especially in detail of recovering shadow areas.