Denoising adversarial networks for rain removal and reflection removal

This paper presents a novel adversarial scheme to perform im- age denoising for the tasks of rain streak removal and reflec- tion removal. Similar to several previous works, our denois- ing adversarial networks first estimate a prior image and then uses it to guide the inference of noise-free image. The novelty of our approach is to jointly learn the gradient and noise-free image based on an adversarial scheme. More specifically, we use the gradient map as the prior image. The inferred noise- free image guided by an estimated gradient is regarded as a negative sample, while the noise-free image guided by the ground truth of a gradient is taken as a positive sample. With the anchor defined by the ground truth of noise-free image, we play a min-max game to jointly train two optimizers for the estimation of the gradient and the inference of noise-free images. We show that both prior image and noise-free image can be accurately obtained under this adversarial scheme. Our state-of-the-art performances achieved on two public bench- mark datasets validate the effectiveness of our approach.Accepted versio