{"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/guided-image-to-image-translation-with-bi-1","title":"Guided Image-to-Image Translation with Bi-Directional Feature Transformation","arxiv_id":"1910.11328","date":"2019-10-24","proceeding":"ICCV 2019 10","authors":["Badour AlBahar","Jia-Bin Huang"],"abstract":"We address the problem of guided image-to-image translation where we translate an input image into another while respecting the constraints provided by an external, user-provided guidance image. Various conditioning methods for leveraging the given guidance image have been explored, including input concatenation , feature concatenation, and conditional affine transformation of feature activations. All these conditioning mechanisms, however, are uni-directional, i.e., no information flow from the input image back to the guidance. To better utilize the constraints of the guidance image, we present a bi-directional feature transformation (bFT) scheme. We show that our bFT scheme outperforms other conditioning schemes and has comparable results to state-of-the-art methods on different tasks.","url_abs":"https://arxiv.org/abs/1910.11328v1","url_pdf":"https://arxiv.org/pdf/1910.11328v1.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":"guided-image-to-image-translation-with-bi-1","repo_url":"https://github.com/vt-vl-lab/Guided-pix2pix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"pose-transfer","task_name":"Pose Transfer"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-reconstruction-on-edge-to-clothes","task":"Image Reconstruction","dataset":"Edge-to-Clothes","model":"bFT","rank_in_archive_order":1,"of":1,"metrics":{"FID":"58.4","LPIPS":"0.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-reconstruction-on-edge-to-handbags","task":"Image Reconstruction","dataset":"Edge-to-Handbags","model":"bFT","rank_in_archive_order":3,"of":4,"metrics":{"FID":"74.9","LPIPS":"0.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-reconstruction-on-edge-to-shoes","task":"Image Reconstruction","dataset":"Edge-to-Shoes","model":"bFT","rank_in_archive_order":3,"of":4,"metrics":{"FID":"121.2","LPIPS":"0.1"},"uses_additional_data":false},{"leaderboard":"/sota/pose-transfer-on-deep-fashion","task":"Pose Transfer","dataset":"Deep-Fashion","model":"bFT","rank_in_archive_order":7,"of":12,"metrics":{"FID":"12.266","IS":"3.22","SSIM":"0.767"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.11328","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}