{"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/photographic-text-to-image-synthesis-with-a","title":"Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network","arxiv_id":"1802.09178","date":"2018-02-26","proceeding":"CVPR 2018 6","authors":["Zizhao Zhang","Yuanpu Xie","Lin Yang"],"abstract":"This paper presents a novel method to deal with the challenging task of\ngenerating photographic images conditioned on semantic image descriptions. Our\nmethod introduces accompanying hierarchical-nested adversarial objectives\ninside the network hierarchies, which regularize mid-level representations and\nassist generator training to capture the complex image statistics. We present\nan extensile single-stream generator architecture to better adapt the jointed\ndiscriminators and push generated images up to high resolutions. We adopt a\nmulti-purpose adversarial loss to encourage more effective image and text\ninformation usage in order to improve the semantic consistency and image\nfidelity simultaneously. Furthermore, we introduce a new visual-semantic\nsimilarity measure to evaluate the semantic consistency of generated images.\nWith extensive experimental validation on three public datasets, our method\nsignificantly improves previous state of the arts on all datasets over\ndifferent evaluation metrics.","url_abs":"http://arxiv.org/abs/1802.09178v2","url_pdf":"http://arxiv.org/pdf/1802.09178v2.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":"photographic-text-to-image-synthesis-with-a","repo_url":"https://github.com/ypxie/HDGan","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.09178","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}