{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/generative-image-inpainting-with-contextual","title":"Generative Image Inpainting with Contextual Attention","arxiv_id":"1801.07892","date":"2018-01-24","proceeding":"CVPR 2018 6","authors":["Jiahui Yu","Zhe Lin","Jimei Yang","Xiaohui Shen","Xin Lu","Thomas S. Huang"],"abstract":"Recent deep learning based approaches have shown promising results for the\nchallenging task of inpainting large missing regions in an image. These methods\ncan generate visually plausible image structures and textures, but often create\ndistorted structures or blurry textures inconsistent with surrounding areas.\nThis is mainly due to ineffectiveness of convolutional neural networks in\nexplicitly borrowing or copying information from distant spatial locations. On\nthe other hand, traditional texture and patch synthesis approaches are\nparticularly suitable when it needs to borrow textures from the surrounding\nregions. Motivated by these observations, we propose a new deep generative\nmodel-based approach which can not only synthesize novel image structures but\nalso explicitly utilize surrounding image features as references during network\ntraining to make better predictions. The model is a feed-forward, fully\nconvolutional neural network which can process images with multiple holes at\narbitrary locations and with variable sizes during the test time. Experiments\non multiple datasets including faces (CelebA, CelebA-HQ), textures (DTD) and\nnatural images (ImageNet, Places2) demonstrate that our proposed approach\ngenerates higher-quality inpainting results than existing ones. Code, demo and\nmodels are available at: https://github.com/JiahuiYu/generative_inpainting.","url_abs":"http://arxiv.org/abs/1801.07892v2","url_pdf":"http://arxiv.org/pdf/1801.07892v2.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":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/JiahuiYu/generative_inpainting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/BaoGevvvv5/photo-restoration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/CS269-Capstone/t-snake-capstone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/CS269-Capstone/t-snake-mask-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/ChopsticksAN/generative_inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/DAA233/generative-inpainting-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/Ir1d/tf-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/ShnitzelKiller/generative_inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/TerminatorSd/generative","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/WonwoongCho/Generative-Inpainting-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/avalonstrel/GatedConvolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/boge8888/Watermark-removal-GUI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/btxuyenHCMUS/generative","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/g2zac/generative_inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/i6092467/semi-supervised-multiview-cbm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/jiajunhua/JiahuiYu-generative_inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/katychou/generative01","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/nuneslu/VeIGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/pfnet-research/Chainer-DeepFill","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/runze-wang-sjtu/generative_inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/sankalpdayal5/Image-Inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/sirius-image-inpainting/Generative-Image-Inpainting-with-Contextual-Attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/spollok/magfield-prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/xurongchao/mv-inpainting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/yunjeongyong/Generative-Inpainting-pytorch-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/zphang/saliency_investigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/zuruoke/watermark-removal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"generative-image-inpainting-with-contextual","repo_url":"https://github.com/JennyVanessa/Deepfill-Paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-inpainting","task_name":"Image Inpainting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.07892","atlas_url":"https://app.syntology.ai/?focus=1801.07892","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1801.07892"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.07892\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.07892"},"call":"get_concepts_for_paper(arxiv_id=\"1801.07892\")"}],"by_repo":[{"repo":"JiahuiYu/generative_inpainting","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BaoGevvvv5/photo-restoration","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CS269-Capstone/t-snake-capstone","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CS269-Capstone/t-snake-mask-generation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ChopsticksAN/generative_inpainting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DAA233/generative-inpainting-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Ir1d/tf-models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ShnitzelKiller/generative_inpainting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"TerminatorSd/generative","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"WonwoongCho/Generative-Inpainting-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"avalonstrel/GatedConvolution","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"boge8888/Watermark-removal-GUI","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"btxuyenHCMUS/generative","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"g2zac/generative_inpainting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"i6092467/semi-supervised-multiview-cbm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jiajunhua/JiahuiYu-generative_inpainting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"katychou/generative01","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nuneslu/VeIGAN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pfnet-research/Chainer-DeepFill","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1806.03589"],"harvested_for_calls":[{"arxiv_id":"1806.03589","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1806.03589"},"call":"get_harvested_code_for_paper(arxiv_id=\"1806.03589\")"}]},{"repo":"runze-wang-sjtu/generative_inpainting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sankalpdayal5/Image-Inpainting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sirius-image-inpainting/Generative-Image-Inpainting-with-Contextual-Attention","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"spollok/magfield-prediction","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xurongchao/mv-inpainting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yunjeongyong/Generative-Inpainting-pytorch-master","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zphang/saliency_investigation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.09750"],"harvested_for_calls":[{"arxiv_id":"2010.09750","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.09750"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.09750\")"}]},{"repo":"zuruoke/watermark-removal","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JennyVanessa/Deepfill-Paddle","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"54ca8e08047e7c31b55fc08e98316b18e676f9e9a22511fd8c38cee77967c031","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}