{"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/auto-retoucherart-a-framework-for-background","title":"Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing","arxiv_id":"1901.03954","date":"2019-01-13","proceeding":null,"authors":["Yunxuan Xiao","Yikai Li","Yuwei Wu","LiZhen Zhu"],"abstract":"Replacing the background and simultaneously adjusting foreground objects is a\nchallenging task in image editing. Current techniques for generating such\nimages relies heavily on user interactions with image editing softwares, which\nis a tedious job for professional retouchers. To reduce their workload, some\nexciting progress has been made on generating images with a given background.\nHowever, these models can neither adjust the position and scale of the\nforeground objects, nor guarantee the semantic consistency between foreground\nand background. To overcome these limitations, we propose a framework --\nART(Auto-Retoucher), to generate images with sufficient semantic and spatial\nconsistency. Images are first processed by semantic matting and scene parsing\nmodules, then a multi-task verifier model will give two confidence scores for\nthe current background and position setting. We demonstrate that our jointly\noptimized verifier model successfully improves the visual consistency, and our\nART framework performs well on images with the human body as foregrounds.","url_abs":"http://arxiv.org/abs/1901.03954v1","url_pdf":"http://arxiv.org/pdf/1901.03954v1.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":"auto-retoucherart-a-framework-for-background","repo_url":"https://github.com/woshiyyya/Auto-Retoucher-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-matting","task_name":"Image Matting"},{"task_slug":null,"task_name":"Position"},{"task_slug":"scene-parsing","task_name":"Scene Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}