{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/discriminative-region-proposal-adversarial","title":"Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation","arxiv_id":"1711.09554","date":"2017-11-27","proceeding":"ECCV 2018 9","authors":["Chao Wang","Haiyong Zheng","Zhibin Yu","Ziqiang Zheng","Zhaorui Gu","Bing Zheng"],"abstract":"Image-to-image translation has been made much progress with embracing\nGenerative Adversarial Networks (GANs). However, it's still very challenging\nfor translation tasks that require high quality, especially at high-resolution\nand photorealism. In this paper, we present Discriminative Region Proposal\nAdversarial Networks (DRPAN) for high-quality image-to-image translation. We\ndecompose the procedure of image-to-image translation task into three iterated\nsteps, first is to generate an image with global structure but some local\nartifacts (via GAN), second is using our DRPnet to propose the most fake region\nfrom the generated image, and third is to implement \"image inpainting\" on the\nmost fake region for more realistic result through a reviser, so that the\nsystem (DRPAN) can be gradually optimized to synthesize images with more\nattention on the most artifact local part. Experiments on a variety of\nimage-to-image translation tasks and datasets validate that our method\noutperforms state-of-the-arts for producing high-quality translation results in\nterms of both human perceptual studies and automatic quantitative measures.","url_abs":"http://arxiv.org/abs/1711.09554v3","url_pdf":"http://arxiv.org/pdf/1711.09554v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"discriminative-region-proposal-adversarial","repo_url":"https://github.com/godisboy/DRPAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}