Joint image-to-image translation with denoising using enhanced generative adversarial networks

作者：

Highlights：

• We study a novel image-to-image translation with noise problem, this is, translating a noisy image in one image domain to a noise-free image in another image domain.

• A trainable end-to-end pipeline and a robust GAN-based model named EGAN are proposed to address this problem.

• We experimentally demonstrate the effectiveness of the proposed pipeline and the superiority of EGAN compared to a range of GAN-based image-to-image translation methods.

摘要

•We study a novel image-to-image translation with noise problem, this is, translating a noisy image in one image domain to a noise-free image in another image domain.•A trainable end-to-end pipeline and a robust GAN-based model named EGAN are proposed to address this problem.•We experimentally demonstrate the effectiveness of the proposed pipeline and the superiority of EGAN compared to a range of GAN-based image-to-image translation methods.

论文关键词：Image-to-image translation,Generative adversarial networks,Image enhancement,Image denoising

论文评审过程：Received 20 May 2020, Revised 13 September 2020, Accepted 7 November 2020, Available online 16 November 2020, Version of Record 19 November 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.116072