{"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/on-the-diversity-of-realistic-image-synthesis","title":"On the Diversity of Realistic Image Synthesis","arxiv_id":"1712.07329","date":"2017-12-20","proceeding":null,"authors":["Zichen Yang","Haifeng Liu","Deng Cai"],"abstract":"Many image processing tasks can be formulated as translating images between\ntwo image domains, such as colorization, super resolution and conditional image\nsynthesis. In most of these tasks, an input image may correspond to multiple\noutputs. However, current existing approaches only show very minor diversity of\nthe outputs. In this paper, we present a novel approach to synthesize diverse\nrealistic images corresponding to a semantic layout. We introduce a diversity\nloss objective, which maximizes the distance between synthesized image pairs\nand links the input noise to the semantic segments in the synthesized images.\nThus, our approach can not only produce diverse images, but also allow users to\nmanipulate the output images by adjusting the noise manually. Experimental\nresults show that images synthesized by our approach are significantly more\ndiverse than that of the current existing works and equipping our diversity\nloss does not degrade the reality of the base networks.","url_abs":"http://arxiv.org/abs/1712.07329v1","url_pdf":"http://arxiv.org/pdf/1712.07329v1.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":"on-the-diversity-of-realistic-image-synthesis","repo_url":"https://github.com/ZJULearning/diverse_image_synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"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}