Image-to-image translation has been made much progress with embracing Generative Adversarial Networks (GANs). However, it’s still very challenging for translation tasks that require high quality, especially at high-resolution and photo-reality. In this work, we present Discriminative Region Proposal Adversarial Network (DRPAN) for high-quality image-to-image translation. We decompose the image-to-image translation procedure into three iterated steps: the first is to generate an image with global structure but some local artifacts (via GAN), the second is to use our Discriminative Region Proposal network (DRPnet) for proposing the most fake region from the generated image, and the third is to implement “image inpainting” on the most fake region for yielding more realistic result through a reviser, so that the system (DRPAN) can be gradually optimized to synthesize images with more attention on the most artifact local part. We explore patch-based GAN to construct DRPnet for proposing the discriminative region to produce masked fake samples, further, we propose a reviser for GANs to distinguish real from masked fake for providing constructive revisions to the generator for producing realistic details, and serve as auxiliaries of the generator to synthesize high-quality results. In addition, we combine pix2pixHD with DRPAN to synthesize high-resolution results with much finer details. Moreover, we improve CycleGAN by DRPAN to address unpaired image-to-image translation with better semantic alignment. Experiments on a variety of paired and unpaired image-to-image translation tasks validate that our method outperforms the state of the art for synthesizing high-quality translation results in terms of both human perceptual studies and automatic quantitative measures. Our code is available at https://github.com/godisboy/DRPAN.

中文翻译：

---

用于高质量图像到图像转换的判别区域提议对抗网络

通过采用生成对抗网络 (GAN)，图像到图像的翻译取得了很大进展。然而，对于需要高质量的翻译任务来说仍然非常具有挑战性，尤其是在高分辨率和照片逼真度方面。在这项工作中，我们提出了用于高质量图像到图像转换的判别区域提议对抗网络 (DRPAN)。我们将图像到图像的转换过程分解为三个迭代步骤：第一个是生成具有全局结构但有一些局部伪影（通过 GAN）的图像，第二个是使用我们的判别区域提议网络（DRPnet）来提议生成图像中最假的区域，第三是在最假的区域上实施“图像修复”，通过修改器产生更逼真的结果，以便系统（DRPAN）可以逐渐优化以合成图像，更多地关注最伪影的局部部分。我们探索基于补丁的 GAN 来构建 DRPnet 以提出判别区域以产生掩码假样本，此外，我们提出了 GAN 的修正器以区分真实与掩码假，以便为生成器提供建设性修改以产生逼真的细节，并作为辅助工具生成器合成高质量的结果。此外，我们将 pix2pixHD 与 DRPAN 相结合，以合成具有更精细细节的高分辨率结果。此外，我们通过 DRPAN 改进 CycleGAN，以通过更好的语义对齐来解决不成对的图像到图像的转换。对各种成对和不成对的图像到图像翻译任务的实验证实，我们的方法在人类感知研究和自动定量测量方面都优于合成高质量翻译结果的最新技术。我们的代码可在 https://github.com/godisboy/DRPAN 获得。