{"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/semi-parametric-image-synthesis","title":"Semi-parametric Image Synthesis","arxiv_id":"1804.10992","date":"2018-04-29","proceeding":"CVPR 2018 6","authors":["Xiaojuan Qi","Qifeng Chen","Jiaya Jia","Vladlen Koltun"],"abstract":"We present a semi-parametric approach to photographic image synthesis from\nsemantic layouts. The approach combines the complementary strengths of\nparametric and nonparametric techniques. The nonparametric component is a\nmemory bank of image segments constructed from a training set of images. Given\na novel semantic layout at test time, the memory bank is used to retrieve\nphotographic references that are provided as source material to a deep network.\nThe synthesis is performed by a deep network that draws on the provided\nphotographic material. Experiments on multiple semantic segmentation datasets\nshow that the presented approach yields considerably more realistic images than\nrecent purely parametric techniques. The results are shown in the supplementary\nvideo at https://youtu.be/U4Q98lenGLQ","url_abs":"http://arxiv.org/abs/1804.10992v1","url_pdf":"http://arxiv.org/pdf/1804.10992v1.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":"semi-parametric-image-synthesis","repo_url":"https://github.com/xjqicuhk/SIMS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-ade20k-outdoor","task":"Image-to-Image Translation","dataset":"ADE20K-Outdoor Labels-to-Photos","model":"SIMS","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"74.7%","FID":"67.7","mIoU":"13.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-cityscapes","task":"Image-to-Image Translation","dataset":"Cityscapes Labels-to-Photo","model":"SIMS","rank_in_archive_order":12,"of":21,"metrics":{"FID":"49.7","Per-pixel Accuracy":"75.5%","mIoU":"47.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.10992","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}