{"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/toward-characteristic-preserving-image-based","title":"Toward Characteristic-Preserving Image-based Virtual Try-On Network","arxiv_id":"1807.07688","date":"2018-07-20","proceeding":"ECCV 2018 9","authors":["Bochao Wang","Huabin Zheng","Xiaodan Liang","Yimin Chen","Liang Lin","Meng Yang"],"abstract":"Image-based virtual try-on systems for fitting new in-shop clothes into a\nperson image have attracted increasing research attention, yet is still\nchallenging. A desirable pipeline should not only transform the target clothes\ninto the most fitting shape seamlessly but also preserve well the clothes\nidentity in the generated image, that is, the key characteristics (e.g.\ntexture, logo, embroidery) that depict the original clothes. However, previous\nimage-conditioned generation works fail to meet these critical requirements\ntowards the plausible virtual try-on performance since they fail to handle\nlarge spatial misalignment between the input image and target clothes. Prior\nwork explicitly tackled spatial deformation using shape context matching, but\nfailed to preserve clothing details due to its coarse-to-fine strategy. In this\nwork, we propose a new fully-learnable Characteristic-Preserving Virtual Try-On\nNetwork(CP-VTON) for addressing all real-world challenges in this task. First,\nCP-VTON learns a thin-plate spline transformation for transforming the in-shop\nclothes into fitting the body shape of the target person via a new Geometric\nMatching Module (GMM) rather than computing correspondences of interest points\nas prior works did. Second, to alleviate boundary artifacts of warped clothes\nand make the results more realistic, we employ a Try-On Module that learns a\ncomposition mask to integrate the warped clothes and the rendered image to\nensure smoothness. Extensive experiments on a fashion dataset demonstrate our\nCP-VTON achieves the state-of-the-art virtual try-on performance both\nqualitatively and quantitatively.","url_abs":"http://arxiv.org/abs/1807.07688v3","url_pdf":"http://arxiv.org/pdf/1807.07688v3.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":"toward-characteristic-preserving-image-based","repo_url":"https://github.com/sergeywong/cp-vton","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"toward-characteristic-preserving-image-based","repo_url":"https://github.com/JaZz-9/Try-First","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"toward-characteristic-preserving-image-based","repo_url":"https://github.com/ankitajaiswal00/Try-First","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"toward-characteristic-preserving-image-based","repo_url":"https://github.com/arunt-sjsu/DL_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"toward-characteristic-preserving-image-based","repo_url":"https://github.com/jiayunz/Virtual-Try-On","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"geometric-matching","task_name":"Geometric Matching"},{"task_slug":"virtual-try-on","task_name":"Virtual Try-on"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.07688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.07688"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/arunt-sjsu/DL_Project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JaZz-9/Try-First","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiayunz/Virtual-Try-On","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sergeywong/cp-vton","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ankitajaiswal00/Try-First","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":"30ce730ccf4be37e","entry":"tensor_for_board","repo":"sergeywong/cp-vton","repo_kind":"official","path":"visualization.py","file_url":"https://github.com/sergeywong/cp-vton/blob/HEAD/visualization.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":"30ce730ccf4be37e"}},{"code_sha256_prefix":"ae4ce56419ea054d","entry":"tensor_list_for_board","repo":"sergeywong/cp-vton","repo_kind":"official","path":"visualization.py","file_url":"https://github.com/sergeywong/cp-vton/blob/HEAD/visualization.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":"ae4ce56419ea054d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}