End-to-end Inception-Unet based Generative Adversarial Networks for Snow and Rain Removals
This work addresses the challenge of atmospheric particle removal in computer vision, which is important for applications like autonomous driving and surveillance, but it is incremental as it builds on existing GAN and U-net architectures.
The paper tackles the problem of removing snow and rain from single images by proposing a global framework with two GANs, one for each particle type, which integrates feature extraction with U-net generators to handle variations in size and appearance, achieving significant improvements over state-of-the-art methods on synthetic and realistic datasets.
The superior performance introduced by deep learning approaches in removing atmospheric particles such as snow and rain from a single image; favors their usage over classical ones. However, deep learning-based approaches still suffer from challenges related to the particle appearance characteristics such as size, type, and transparency. Furthermore, due to the unique characteristics of rain and snow particles, single network based deep learning approaches struggle in handling both degradation scenarios simultaneously. In this paper, a global framework that consists of two Generative Adversarial Networks (GANs) is proposed where each handles the removal of each particle individually. The architectures of both desnowing and deraining GANs introduce the integration of a feature extraction phase with the classical U-net generator network which in turn enhances the removal performance in the presence of severe variations in size and appearance. Furthermore, a realistic dataset that contains pairs of snowy images next to their groundtruth images estimated using a low-rank approximation approach; is presented. The experiments show that the proposed desnowing and deraining approaches achieve significant improvements in comparison to the state-of-the-art approaches when tested on both synthetic and realistic datasets.