{"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/stableviton-learning-semantic-correspondence","title":"StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On","arxiv_id":"2312.01725","date":"2023-12-04","proceeding":"CVPR 2024 1","authors":["Jeongho Kim","Gyojung Gu","Minho Park","Sunghyun Park","Jaegul Choo"],"abstract":"Given a clothing image and a person image, an image-based virtual try-on aims to generate a customized image that appears natural and accurately reflects the characteristics of the clothing image. In this work, we aim to expand the applicability of the pre-trained diffusion model so that it can be utilized independently for the virtual try-on task.The main challenge is to preserve the clothing details while effectively utilizing the robust generative capability of the pre-trained model. In order to tackle these issues, we propose StableVITON, learning the semantic correspondence between the clothing and the human body within the latent space of the pre-trained diffusion model in an end-to-end manner. Our proposed zero cross-attention blocks not only preserve the clothing details by learning the semantic correspondence but also generate high-fidelity images by utilizing the inherent knowledge of the pre-trained model in the warping process. Through our proposed novel attention total variation loss and applying augmentation, we achieve the sharp attention map, resulting in a more precise representation of clothing details. StableVITON outperforms the baselines in qualitative and quantitative evaluation, showing promising quality in arbitrary person images. Our code is available at https://github.com/rlawjdghek/StableVITON.","url_abs":"https://arxiv.org/abs/2312.01725v1","url_pdf":"https://arxiv.org/pdf/2312.01725v1.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":"stableviton-learning-semantic-correspondence","repo_url":"https://github.com/rlawjdghek/stableviton","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"},{"task_slug":"virtual-try-on","task_name":"Virtual Try-on"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/virtual-try-on-on-viton-hd","task":"Virtual Try-on","dataset":"VITON-HD","model":"StableVITON","rank_in_archive_order":3,"of":5,"metrics":{"FID":"8.233"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.01725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01725"}},"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/rlawjdghek/stableviton","reach":{"status":"ok"}}],"summary":{"ran":7,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":11,"samples":[{"code_sha256_prefix":"c45d0ed437091615","entry":"imread","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c45d0ed437091615"}},{"code_sha256_prefix":"baac2b2475063789","entry":"imread_for_albu","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"baac2b2475063789"}},{"code_sha256_prefix":"aa89e00bbdd4ea69","entry":"load_args","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"utils.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa89e00bbdd4ea69"}},{"code_sha256_prefix":"416b5f44335294a3","entry":"norm_for_albu","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"416b5f44335294a3"}},{"code_sha256_prefix":"d9fe87f7075657f3","entry":"resize_mask","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"utils.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d9fe87f7075657f3"}},{"code_sha256_prefix":"29e5e72bcd006dcd","entry":"spatial_average","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"eval_models/networks_basic.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/eval_models/networks_basic.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29e5e72bcd006dcd"}},{"code_sha256_prefix":"c42ff87e4ec6ca40","entry":"tensor2img","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"utils.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c42ff87e4ec6ca40"}},{"code_sha256_prefix":"351677a36e1961df","entry":"upsample","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"eval_models/networks_basic.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/eval_models/networks_basic.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"351677a36e1961df"}},{"code_sha256_prefix":"cfc17707f35e7ec4","entry":"get_state_dict","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"cldm/model.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/cldm/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cfc17707f35e7ec4"}},{"code_sha256_prefix":"35ad646f5b9e8cbf","entry":"load_state_dict","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"cldm/model.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/cldm/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35ad646f5b9e8cbf"}},{"code_sha256_prefix":"dfd2379e29a03aef","entry":"score_2afc_dataset","repo":"rlawjdghek/stableviton","repo_kind":"official","path":"eval_models/dist_model.py","file_url":"https://github.com/rlawjdghek/stableviton/blob/HEAD/eval_models/dist_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dfd2379e29a03aef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}