{"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/user-guided-deep-anime-line-art-colorization","title":"User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks","arxiv_id":"1808.03240","date":"2018-08-09","proceeding":null,"authors":["Yuanzheng Ci","Xinzhu Ma","Zhihui Wang","Haojie Li","Zhongxuan Luo"],"abstract":"Scribble colors based line art colorization is a challenging computer vision\nproblem since neither greyscale values nor semantic information is presented in\nline arts, and the lack of authentic illustration-line art training pairs also\nincreases difficulty of model generalization. Recently, several Generative\nAdversarial Nets (GANs) based methods have achieved great success. They can\ngenerate colorized illustrations conditioned on given line art and color hints.\nHowever, these methods fail to capture the authentic illustration distributions\nand are hence perceptually unsatisfying in the sense that they often lack\naccurate shading. To address these challenges, we propose a novel deep\nconditional adversarial architecture for scribble based anime line art\ncolorization. Specifically, we integrate the conditional framework with WGAN-GP\ncriteria as well as the perceptual loss to enable us to robustly train a deep\nnetwork that makes the synthesized images more natural and real. We also\nintroduce a local features network that is independent of synthetic data. With\nGANs conditioned on features from such network, we notably increase the\ngeneralization capability over \"in the wild\" line arts. Furthermore, we collect\ntwo datasets that provide high-quality colorful illustrations and authentic\nline arts for training and benchmarking. With the proposed model trained on our\nillustration dataset, we demonstrate that images synthesized by the presented\napproach are considerably more realistic and precise than alternative\napproaches.","url_abs":"http://arxiv.org/abs/1808.03240v2","url_pdf":"http://arxiv.org/pdf/1808.03240v2.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":"user-guided-deep-anime-line-art-colorization","repo_url":"https://github.com/orashi/AlacGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"user-guided-deep-anime-line-art-colorization","repo_url":"https://github.com/n1kkqt/line-art-colorization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"line-art-colorization","task_name":"Line Art Colorization"}],"methods":[{"method_slug":"colorization","method_name":"Colorization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.03240","atlas_url":"https://app.syntology.ai/?focus=1808.03240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.03240"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/n1kkqt/line-art-colorization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/orashi/AlacGAN","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8df6be84b5a210cd","entry":"create_logger","repo":"orashi/AlacGAN","repo_kind":"official","path":"utils/io.py","file_url":"https://github.com/orashi/AlacGAN/blob/HEAD/utils/io.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8df6be84b5a210cd"}},{"code_sha256_prefix":"768d8998674638f6","entry":"load_state","repo":"orashi/AlacGAN","repo_kind":"official","path":"utils/io.py","file_url":"https://github.com/orashi/AlacGAN/blob/HEAD/utils/io.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"768d8998674638f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}