{"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/generative-visual-manipulation-on-the-natural","title":"Generative Visual Manipulation on the Natural Image Manifold","arxiv_id":"1609.03552","date":"2016-09-12","proceeding":null,"authors":["Jun-Yan Zhu","Philipp Krähenbühl","Eli Shechtman","Alexei A. Efros"],"abstract":"Realistic image manipulation is challenging because it requires modifying the\nimage appearance in a user-controlled way, while preserving the realism of the\nresult. Unless the user has considerable artistic skill, it is easy to \"fall\noff\" the manifold of natural images while editing. In this paper, we propose to\nlearn the natural image manifold directly from data using a generative\nadversarial neural network. We then define a class of image editing operations,\nand constrain their output to lie on that learned manifold at all times. The\nmodel automatically adjusts the output keeping all edits as realistic as\npossible. All our manipulations are expressed in terms of constrained\noptimization and are applied in near-real time. We evaluate our algorithm on\nthe task of realistic photo manipulation of shape and color. The presented\nmethod can further be used for changing one image to look like the other, as\nwell as generating novel imagery from scratch based on user's scribbles.","url_abs":"http://arxiv.org/abs/1609.03552v3","url_pdf":"http://arxiv.org/pdf/1609.03552v3.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-visual-manipulation-on-the-natural","repo_url":"https://github.com/junyanz/iGAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-manipulation","task_name":"Image Manipulation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.03552","atlas_url":"https://app.syntology.ai/?focus=1609.03552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.03552"}},"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/junyanz/iGAN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"5c63f9294d8b5d57","entry":"preprocess_image","repo":"junyanz/iGAN","repo_kind":"official","path":"iGAN_script.py","file_url":"https://github.com/junyanz/iGAN/blob/HEAD/iGAN_script.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":"5c63f9294d8b5d57"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}