{"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/mc-gan-multi-conditional-generative","title":"MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis","arxiv_id":"1805.01123","date":"2018-05-03","proceeding":null,"authors":["Hyojin Park","YoungJoon Yoo","Nojun Kwak"],"abstract":"In this paper, we introduce a new method for generating an object image from\ntext attributes on a desired location, when the base image is given. One step\nfurther to the existing studies on text-to-image generation mainly focusing on\nthe object's appearance, the proposed method aims to generate an object image\npreserving the given background information, which is the first attempt in this\nfield. To tackle the problem, we propose a multi-conditional GAN (MC-GAN) which\ncontrols both the object and background information jointly. As a core\ncomponent of MC-GAN, we propose a synthesis block which disentangles the object\nand background information in the training stage. This block enables MC-GAN to\ngenerate a realistic object image with the desired background by controlling\nthe amount of the background information from the given base image using the\nforeground information from the text attributes. From the experiments with\nCaltech-200 bird and Oxford-102 flower datasets, we show that our model is able\nto generate photo-realistic images with a resolution of 128 x 128. The source\ncode of MC-GAN is released.","url_abs":"http://arxiv.org/abs/1805.01123v5","url_pdf":"http://arxiv.org/pdf/1805.01123v5.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":"mc-gan-multi-conditional-generative","repo_url":"https://github.com/HYOJINPARK/MC_GAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mc-gan-multi-conditional-generative","repo_url":"https://github.com/yangyucheng000/papercode-2/tree/main/MC-GRA_Mindscope-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}