Prior-DualGAN: Rain rendering from coarse to fine

Abstract

The success of deep neural networks (DNN) in deraining has led to increased research in rain rendering. In this paper, we introduce a novel Prior-DualGAN algorithm to synthesize diverse and realistic rainy/non-rainy image pairs to improve DNN training for deraining. More precisely, the rain streak prior is first generated using essential rain streak attributes; then more realistic and diverse rain streak patterns are rendered by the first generator; finally, the second generator naturally fuses the background and generated rain streaks to produce the final rainy images. Our method has two main advantages: (1) the rain streak prior enables the network to incorporate physical prior knowledge, accelerating network convergence; (2) our dual GAN approach gradually improves the naturalness and diversity of synthesized rainy images from rain streak synthesis to rainy image synthesis. We evaluate deraining algorithms using our generated rain-augmented Rain100L, Rain14000, and Rain-Vehicle dataset, and show significant performance improvements. We evaluate existing deraining algorithms using our generated rain-augmented datasets Rain100L, Rain14000, and Rain-Vehicle, verifying that training with our generated rain-augmented datasets significantly improves the deraining effect. The source code will be released shortly after article’s acceptance.